diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -2,7 +2,7 @@ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, - "global_step": 1784, + "global_step": 892, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, @@ -10,10745 +10,5375 @@ { "epoch": 0.0, "learning_rate": 0.0, - "loss": 4.9004, + "loss": 4.7965, "step": 1 }, { "epoch": 0.0, "learning_rate": 0.0, - "loss": 5.028, + "loss": 5.0502, "step": 2 }, { "epoch": 0.0, "learning_rate": 2e-06, - "loss": 5.1215, + "loss": 4.9118, "step": 3 }, { "epoch": 0.0, "learning_rate": 4e-06, - "loss": 4.6759, + "loss": 4.8924, "step": 4 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 6e-06, - "loss": 4.7525, + "loss": 4.713, "step": 5 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 8e-06, - "loss": 4.7486, + "loss": 4.7862, "step": 6 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 1e-05, - "loss": 4.5801, + "loss": 4.7066, "step": 7 }, { - "epoch": 0.0, + "epoch": 0.01, "learning_rate": 1.2e-05, - "loss": 4.6594, + "loss": 4.5681, "step": 8 }, { "epoch": 0.01, "learning_rate": 1.4e-05, - "loss": 4.831, + "loss": 4.6685, "step": 9 }, { "epoch": 0.01, "learning_rate": 1.6e-05, - "loss": 4.4698, + "loss": 4.4888, "step": 10 }, { "epoch": 0.01, "learning_rate": 1.8e-05, - "loss": 4.513, + "loss": 4.566, "step": 11 }, { "epoch": 0.01, "learning_rate": 2e-05, - "loss": 4.4364, + "loss": 4.4834, "step": 12 }, { "epoch": 0.01, "learning_rate": 2.2e-05, - "loss": 4.5931, + "loss": 4.4308, "step": 13 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 2.4e-05, - "loss": 4.2523, + "loss": 4.3983, "step": 14 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 2.6e-05, - "loss": 4.3758, + "loss": 4.3274, "step": 15 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 2.8e-05, - "loss": 4.4732, + "loss": 4.4187, "step": 16 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 3e-05, - "loss": 4.4427, + "loss": 4.4051, "step": 17 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 3.2e-05, - "loss": 4.3388, + "loss": 4.5591, "step": 18 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 3.4000000000000007e-05, - "loss": 4.285, + "loss": 4.2522, "step": 19 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 3.6e-05, - "loss": 4.6023, + "loss": 4.4396, "step": 20 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 3.8e-05, - "loss": 4.3002, + "loss": 4.341, "step": 21 }, { - "epoch": 0.01, + "epoch": 0.02, "learning_rate": 4e-05, - "loss": 4.6864, + "loss": 4.3206, "step": 22 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 4.2000000000000004e-05, - "loss": 4.4214, + "loss": 4.3652, "step": 23 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 4.4e-05, - "loss": 4.2052, + "loss": 4.4403, "step": 24 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 4.6e-05, - "loss": 4.3643, + "loss": 4.3302, "step": 25 }, { - "epoch": 0.01, + "epoch": 0.03, "learning_rate": 4.8e-05, - "loss": 4.5151, + "loss": 4.5044, "step": 26 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 5e-05, - "loss": 4.3193, + "loss": 4.2454, "step": 27 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 5.2e-05, - "loss": 4.032, + "loss": 4.1507, "step": 28 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 5.4e-05, - "loss": 4.341, + "loss": 4.1699, "step": 29 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 5.6e-05, - "loss": 4.2808, + "loss": 4.3846, "step": 30 }, { - "epoch": 0.02, + "epoch": 0.03, "learning_rate": 5.800000000000001e-05, - "loss": 4.215, + "loss": 4.3922, "step": 31 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 6e-05, - "loss": 4.5311, + "loss": 4.1628, "step": 32 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 6.2e-05, - "loss": 4.2728, + "loss": 4.2404, "step": 33 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 6.4e-05, - "loss": 4.107, + "loss": 4.1711, "step": 34 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 6.6e-05, - "loss": 4.3486, + "loss": 4.3801, "step": 35 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 6.800000000000001e-05, - "loss": 4.674, + "loss": 4.3257, "step": 36 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 7.000000000000001e-05, - "loss": 4.2681, + "loss": 4.3421, "step": 37 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 7.2e-05, - "loss": 4.4542, + "loss": 4.3652, "step": 38 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 7.4e-05, - "loss": 4.5041, + "loss": 4.5053, "step": 39 }, { - "epoch": 0.02, + "epoch": 0.04, "learning_rate": 7.6e-05, - "loss": 4.5944, + "loss": 4.3429, "step": 40 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 7.8e-05, - "loss": 4.3392, + "loss": 4.2031, "step": 41 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 8e-05, - "loss": 4.1578, + "loss": 4.3582, "step": 42 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 8.2e-05, - "loss": 4.4119, + "loss": 4.1308, "step": 43 }, { - "epoch": 0.02, + "epoch": 0.05, "learning_rate": 8.400000000000001e-05, - "loss": 4.2466, + "loss": 4.3577, "step": 44 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 8.599999999999999e-05, - "loss": 4.5696, + "loss": 4.3479, "step": 45 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 8.8e-05, - "loss": 4.5456, + "loss": 4.552, "step": 46 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 8.999999999999999e-05, - "loss": 4.6251, + "loss": 4.3865, "step": 47 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 9.2e-05, - "loss": 4.8245, + "loss": 4.7344, "step": 48 }, { - "epoch": 0.03, + "epoch": 0.05, "learning_rate": 9.400000000000001e-05, - "loss": 4.8404, + "loss": 4.8671, "step": 49 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 9.6e-05, - "loss": 4.957, + "loss": 4.6237, "step": 50 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 9.800000000000001e-05, - "loss": 4.3029, + "loss": 4.2275, "step": 51 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 0.0001, - "loss": 4.4912, + "loss": 4.4134, "step": 52 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 0.000102, - "loss": 4.4324, + "loss": 4.2124, "step": 53 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 0.000104, - "loss": 4.3132, + "loss": 4.2647, "step": 54 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 0.000106, - "loss": 4.4116, + "loss": 4.2844, "step": 55 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 0.000108, - "loss": 4.4468, + "loss": 4.3499, "step": 56 }, { - "epoch": 0.03, + "epoch": 0.06, "learning_rate": 0.00011, - "loss": 4.3603, + "loss": 4.3192, "step": 57 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 0.000112, - "loss": 4.3377, + "loss": 4.5597, "step": 58 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 0.000114, - "loss": 4.3845, + "loss": 4.3034, "step": 59 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 0.00011600000000000001, - "loss": 4.3166, + "loss": 4.2302, "step": 60 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 0.000118, - "loss": 4.4813, + "loss": 4.4397, "step": 61 }, { - "epoch": 0.03, + "epoch": 0.07, "learning_rate": 0.00012, - "loss": 4.3453, + "loss": 4.4027, "step": 62 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 0.000122, - "loss": 4.7119, + "loss": 4.2169, "step": 63 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 0.000124, - "loss": 4.1777, + "loss": 4.3468, "step": 64 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 0.000126, - "loss": 4.3867, + "loss": 4.1751, "step": 65 }, { - "epoch": 0.04, + "epoch": 0.07, "learning_rate": 0.000128, - "loss": 4.5375, + "loss": 4.3815, "step": 66 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.00013000000000000002, - "loss": 4.4507, + "loss": 4.1777, "step": 67 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.000132, - "loss": 4.5104, + "loss": 4.2333, "step": 68 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.000134, - "loss": 4.5196, + "loss": 4.1581, "step": 69 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.00013600000000000003, - "loss": 4.3081, + "loss": 4.3495, "step": 70 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.00013800000000000002, - "loss": 4.4306, + "loss": 4.5026, "step": 71 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.00014000000000000001, - "loss": 4.1549, + "loss": 4.4102, "step": 72 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.00014199999999999998, - "loss": 4.519, + "loss": 4.3022, "step": 73 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.000144, - "loss": 4.2824, + "loss": 4.3463, "step": 74 }, { - "epoch": 0.04, + "epoch": 0.08, "learning_rate": 0.000146, - "loss": 4.8346, + "loss": 4.2018, "step": 75 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 0.000148, - "loss": 4.5079, + "loss": 4.4457, "step": 76 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 0.00015, - "loss": 4.4211, + "loss": 4.3321, "step": 77 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 0.000152, - "loss": 4.2884, + "loss": 4.3216, "step": 78 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 0.000154, - "loss": 4.515, + "loss": 4.1577, "step": 79 }, { - "epoch": 0.04, + "epoch": 0.09, "learning_rate": 0.000156, - "loss": 4.6273, + "loss": 4.4279, "step": 80 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 0.000158, - "loss": 4.3338, + "loss": 4.4479, "step": 81 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 0.00016, - "loss": 4.5265, + "loss": 4.2937, "step": 82 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 0.000162, - "loss": 4.3343, + "loss": 4.8258, "step": 83 }, { - "epoch": 0.05, + "epoch": 0.09, "learning_rate": 0.000164, - "loss": 4.5901, + "loss": 4.4215, "step": 84 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.00016600000000000002, - "loss": 4.5625, + "loss": 4.4092, "step": 85 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.00016800000000000002, - "loss": 4.3965, + "loss": 4.3837, "step": 86 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.00017, - "loss": 4.8006, + "loss": 4.3505, "step": 87 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.00017199999999999998, - "loss": 4.2901, + "loss": 4.3491, "step": 88 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.000174, - "loss": 4.723, + "loss": 4.4475, "step": 89 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.000176, - "loss": 4.2745, + "loss": 4.3947, "step": 90 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.000178, - "loss": 4.7077, + "loss": 4.7094, "step": 91 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.00017999999999999998, - "loss": 4.2875, + "loss": 4.5694, "step": 92 }, { - "epoch": 0.05, + "epoch": 0.1, "learning_rate": 0.000182, - "loss": 4.1907, + "loss": 4.2909, "step": 93 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 0.000184, - "loss": 4.8955, + "loss": 4.4371, "step": 94 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 0.000186, - "loss": 4.763, + "loss": 4.7291, "step": 95 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 0.00018800000000000002, - "loss": 4.6358, + "loss": 4.6914, "step": 96 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 0.00019, - "loss": 4.8524, + "loss": 4.5874, "step": 97 }, { - "epoch": 0.05, + "epoch": 0.11, "learning_rate": 0.000192, - "loss": 4.6766, + "loss": 4.7773, "step": 98 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 0.000194, - "loss": 4.8759, + "loss": 4.4424, "step": 99 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 0.00019600000000000002, - "loss": 4.8744, + "loss": 4.7924, "step": 100 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 0.00019800000000000002, - "loss": 5.0054, + "loss": 4.5736, "step": 101 }, { - "epoch": 0.06, + "epoch": 0.11, "learning_rate": 0.0002, - "loss": 4.6005, + "loss": 4.6228, "step": 102 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000202, - "loss": 5.1411, + "loss": 4.4887, "step": 103 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000204, - "loss": 4.7481, + "loss": 4.4669, "step": 104 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000206, - "loss": 4.7446, + "loss": 4.485, "step": 105 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000208, - "loss": 4.646, + "loss": 4.4893, "step": 106 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.00021, - "loss": 4.7589, + "loss": 4.5879, "step": 107 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000212, - "loss": 4.8083, + "loss": 4.6778, "step": 108 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000214, - "loss": 4.602, + "loss": 4.2605, "step": 109 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000216, - "loss": 4.8205, + "loss": 4.431, "step": 110 }, { - "epoch": 0.06, + "epoch": 0.12, "learning_rate": 0.000218, - "loss": 4.9484, + "loss": 4.52, "step": 111 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 0.00022, - "loss": 4.4804, + "loss": 4.5446, "step": 112 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 0.000222, - "loss": 4.6857, + "loss": 4.4884, "step": 113 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 0.000224, - "loss": 4.513, + "loss": 4.3684, "step": 114 }, { - "epoch": 0.06, + "epoch": 0.13, "learning_rate": 0.00022600000000000002, - "loss": 4.3616, + "loss": 4.5161, "step": 115 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 0.000228, - "loss": 4.4706, + "loss": 4.1576, "step": 116 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 0.00023, - "loss": 4.8255, + "loss": 4.4825, "step": 117 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 0.00023200000000000003, - "loss": 5.3022, + "loss": 4.3964, "step": 118 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 0.00023400000000000002, - "loss": 4.7448, + "loss": 4.5091, "step": 119 }, { - "epoch": 0.07, + "epoch": 0.13, "learning_rate": 0.000236, - "loss": 4.9612, + "loss": 4.5291, "step": 120 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.00023799999999999998, - "loss": 5.0743, + "loss": 4.4232, "step": 121 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.00024, - "loss": 4.6597, + "loss": 4.4717, "step": 122 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.000242, - "loss": 4.6022, + "loss": 4.274, "step": 123 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.000244, - "loss": 4.8359, + "loss": 4.4989, "step": 124 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.000246, - "loss": 4.4029, + "loss": 4.55, "step": 125 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.000248, - "loss": 4.8278, + "loss": 4.5464, "step": 126 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.00025, - "loss": 4.6141, + "loss": 4.5534, "step": 127 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.000252, - "loss": 5.0218, + "loss": 4.4587, "step": 128 }, { - "epoch": 0.07, + "epoch": 0.14, "learning_rate": 0.000254, - "loss": 5.1366, + "loss": 4.3396, "step": 129 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 0.000256, - "loss": 5.0889, + "loss": 4.6201, "step": 130 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 0.00025800000000000004, - "loss": 5.4884, + "loss": 4.4956, "step": 131 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 0.00026000000000000003, - "loss": 4.5957, + "loss": 4.6595, "step": 132 }, { - "epoch": 0.07, + "epoch": 0.15, "learning_rate": 0.000262, - "loss": 5.5934, + "loss": 4.5596, "step": 133 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 0.000264, - "loss": 4.8525, + "loss": 4.6203, "step": 134 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 0.000266, - "loss": 4.6521, + "loss": 4.3535, "step": 135 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 0.000268, - "loss": 5.2984, + "loss": 4.4372, "step": 136 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 0.00027, - "loss": 5.3753, + "loss": 4.684, "step": 137 }, { - "epoch": 0.08, + "epoch": 0.15, "learning_rate": 0.00027200000000000005, - "loss": 5.6616, + "loss": 5.0621, "step": 138 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00027400000000000005, - "loss": 5.0541, + "loss": 4.5093, "step": 139 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00027600000000000004, - "loss": 4.6721, + "loss": 4.4214, "step": 140 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00027800000000000004, - "loss": 6.1673, + "loss": 4.7394, "step": 141 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00028000000000000003, - "loss": 5.0666, + "loss": 4.7751, "step": 142 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00028199999999999997, - "loss": 4.759, + "loss": 4.6543, "step": 143 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00028399999999999996, - "loss": 5.2774, + "loss": 4.5343, "step": 144 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00028599999999999996, - "loss": 5.2152, + "loss": 5.3579, "step": 145 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.000288, - "loss": 5.1393, + "loss": 4.9072, "step": 146 }, { - "epoch": 0.08, + "epoch": 0.16, "learning_rate": 0.00029, - "loss": 5.1248, + "loss": 4.7826, "step": 147 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 0.000292, - "loss": 4.9999, + "loss": 4.6273, "step": 148 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 0.000294, - "loss": 5.2187, + "loss": 5.0711, "step": 149 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 0.000296, - "loss": 9.4461, + "loss": 4.6724, "step": 150 }, { - "epoch": 0.08, + "epoch": 0.17, "learning_rate": 0.000298, - "loss": 4.975, + "loss": 4.8402, "step": 151 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 0.0003, - "loss": 5.4119, + "loss": 4.9597, "step": 152 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 0.000302, - "loss": 4.7027, + "loss": 4.8801, "step": 153 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 0.000304, - "loss": 6.0914, + "loss": 4.5698, "step": 154 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 0.000306, - "loss": 4.8098, + "loss": 4.5396, "step": 155 }, { - "epoch": 0.09, + "epoch": 0.17, "learning_rate": 0.000308, - "loss": 5.2307, + "loss": 4.7222, "step": 156 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.00031, - "loss": 5.0387, + "loss": 5.0516, "step": 157 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.000312, - "loss": 4.9038, + "loss": 4.8873, "step": 158 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.000314, - "loss": 5.2071, + "loss": 4.9982, "step": 159 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.000316, - "loss": 6.1251, + "loss": 4.7088, "step": 160 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.00031800000000000003, - "loss": 5.1208, + "loss": 4.6326, "step": 161 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.00032, - "loss": 5.3454, + "loss": 4.636, "step": 162 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.000322, - "loss": 5.2355, + "loss": 4.6224, "step": 163 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.000324, - "loss": 5.0276, + "loss": 4.8179, "step": 164 }, { - "epoch": 0.09, + "epoch": 0.18, "learning_rate": 0.000326, - "loss": 5.1945, + "loss": 4.6294, "step": 165 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 0.000328, - "loss": 5.3061, + "loss": 4.7156, "step": 166 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 0.00033, - "loss": 4.8918, + "loss": 4.6405, "step": 167 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 0.00033200000000000005, - "loss": 4.6604, + "loss": 4.5294, "step": 168 }, { - "epoch": 0.09, + "epoch": 0.19, "learning_rate": 0.00033400000000000004, - "loss": 4.7092, + "loss": 5.4458, "step": 169 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.00033600000000000004, - "loss": 4.8231, + "loss": 4.7599, "step": 170 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.00033800000000000003, - "loss": 4.9869, + "loss": 4.8152, "step": 171 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.00034, - "loss": 6.1004, + "loss": 4.9118, "step": 172 }, { - "epoch": 0.1, + "epoch": 0.19, "learning_rate": 0.000342, - "loss": 4.9545, + "loss": 4.6432, "step": 173 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00034399999999999996, - "loss": 4.9919, + "loss": 4.5836, "step": 174 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.000346, - "loss": 5.9775, + "loss": 4.5978, "step": 175 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.000348, - "loss": 4.6924, + "loss": 4.6663, "step": 176 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00035, - "loss": 4.7249, + "loss": 4.7834, "step": 177 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.000352, - "loss": 4.8362, + "loss": 4.6238, "step": 178 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.000354, - "loss": 4.742, + "loss": 4.6915, "step": 179 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.000356, - "loss": 5.4143, + "loss": 4.7074, "step": 180 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.000358, - "loss": 5.3781, + "loss": 4.6754, "step": 181 }, { - "epoch": 0.1, + "epoch": 0.2, "learning_rate": 0.00035999999999999997, - "loss": 4.8513, + "loss": 4.751, "step": 182 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.000362, - "loss": 5.3895, + "loss": 4.653, "step": 183 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.000364, - "loss": 4.8767, + "loss": 4.9619, "step": 184 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.000366, - "loss": 5.1958, + "loss": 4.8057, "step": 185 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.000368, - "loss": 5.6795, + "loss": 4.6844, "step": 186 }, { - "epoch": 0.1, + "epoch": 0.21, "learning_rate": 0.00037, - "loss": 4.7545, + "loss": 4.8071, "step": 187 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.000372, - "loss": 5.1963, + "loss": 4.5574, "step": 188 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.000374, - "loss": 5.2655, + "loss": 4.65, "step": 189 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.00037600000000000003, - "loss": 5.3899, + "loss": 4.6756, "step": 190 }, { - "epoch": 0.11, + "epoch": 0.21, "learning_rate": 0.000378, - "loss": 5.6963, + "loss": 4.7344, "step": 191 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.00038, - "loss": 5.6408, + "loss": 4.8258, "step": 192 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.000382, - "loss": 5.4532, + "loss": 4.8066, "step": 193 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.000384, - "loss": 4.786, + "loss": 4.6763, "step": 194 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.000386, - "loss": 5.8778, + "loss": 5.9026, "step": 195 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.000388, - "loss": 5.3354, + "loss": 5.2934, "step": 196 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.00039000000000000005, - "loss": 6.192, + "loss": 5.1461, "step": 197 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.00039200000000000004, - "loss": 4.9989, + "loss": 7.1754, "step": 198 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.00039400000000000004, - "loss": 5.6707, + "loss": 5.788, "step": 199 }, { - "epoch": 0.11, + "epoch": 0.22, "learning_rate": 0.00039600000000000003, - "loss": 5.7178, + "loss": 5.1586, "step": 200 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.000398, - "loss": 5.6302, + "loss": 4.9359, "step": 201 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.0004, - "loss": 4.9545, + "loss": 5.1274, "step": 202 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.000402, - "loss": 5.2248, + "loss": 5.4457, "step": 203 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.000404, - "loss": 5.4006, + "loss": 4.8784, "step": 204 }, { - "epoch": 0.11, + "epoch": 0.23, "learning_rate": 0.00040600000000000006, - "loss": 4.8793, + "loss": 4.7054, "step": 205 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.000408, - "loss": 5.8477, + "loss": 4.8631, "step": 206 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.00041, - "loss": 5.0031, + "loss": 4.7219, "step": 207 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.000412, - "loss": 5.7179, + "loss": 4.5005, "step": 208 }, { - "epoch": 0.12, + "epoch": 0.23, "learning_rate": 0.000414, - "loss": 4.9885, + "loss": 4.7144, "step": 209 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000416, - "loss": 5.2685, + "loss": 4.8477, "step": 210 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00041799999999999997, - "loss": 4.9536, + "loss": 4.9471, "step": 211 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00042, - "loss": 5.6715, + "loss": 4.8034, "step": 212 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000422, - "loss": 5.6695, + "loss": 4.9817, "step": 213 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000424, - "loss": 4.7195, + "loss": 4.8543, "step": 214 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000426, - "loss": 5.8662, + "loss": 4.5916, "step": 215 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000428, - "loss": 4.6152, + "loss": 4.8308, "step": 216 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.00043, - "loss": 5.5386, + "loss": 5.0146, "step": 217 }, { - "epoch": 0.12, + "epoch": 0.24, "learning_rate": 0.000432, - "loss": 4.8669, + "loss": 4.7929, "step": 218 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.00043400000000000003, - "loss": 4.9958, + "loss": 4.7524, "step": 219 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.000436, - "loss": 5.9084, + "loss": 4.9242, "step": 220 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.000438, - "loss": 5.1762, + "loss": 4.6412, "step": 221 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.00044, - "loss": 5.9058, + "loss": 4.7249, "step": 222 }, { - "epoch": 0.12, + "epoch": 0.25, "learning_rate": 0.000442, - "loss": 4.9857, + "loss": 4.9072, "step": 223 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.000444, - "loss": 4.9554, + "loss": 4.7815, "step": 224 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.000446, - "loss": 5.1024, + "loss": 4.9337, "step": 225 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.000448, - "loss": 5.246, + "loss": 4.988, "step": 226 }, { - "epoch": 0.13, + "epoch": 0.25, "learning_rate": 0.00045000000000000004, - "loss": 5.1045, + "loss": 4.9625, "step": 227 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00045200000000000004, - "loss": 4.799, + "loss": 5.0409, "step": 228 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00045400000000000003, - "loss": 5.0115, + "loss": 5.2279, "step": 229 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.000456, - "loss": 4.9686, + "loss": 5.0434, "step": 230 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.000458, - "loss": 4.9534, + "loss": 5.5576, "step": 231 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00046, - "loss": 5.2565, + "loss": 4.9453, "step": 232 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.000462, - "loss": 5.3499, + "loss": 4.8898, "step": 233 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00046400000000000006, - "loss": 5.0755, + "loss": 4.9863, "step": 234 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00046600000000000005, - "loss": 4.7707, + "loss": 5.1805, "step": 235 }, { - "epoch": 0.13, + "epoch": 0.26, "learning_rate": 0.00046800000000000005, - "loss": 5.6232, + "loss": 4.7755, "step": 236 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.00047, - "loss": 5.0501, + "loss": 4.703, "step": 237 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.000472, - "loss": 6.3229, + "loss": 5.0463, "step": 238 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.000474, - "loss": 5.5726, + "loss": 4.7303, "step": 239 }, { - "epoch": 0.13, + "epoch": 0.27, "learning_rate": 0.00047599999999999997, - "loss": 5.805, + "loss": 4.8589, "step": 240 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.00047799999999999996, - "loss": 5.5205, + "loss": 4.9848, "step": 241 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.00048, - "loss": 5.2144, + "loss": 5.3981, "step": 242 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.000482, - "loss": 5.8397, + "loss": 5.5512, "step": 243 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.000484, - "loss": 5.5656, + "loss": 4.8617, "step": 244 }, { - "epoch": 0.14, + "epoch": 0.27, "learning_rate": 0.000486, - "loss": 5.3271, + "loss": 5.081, "step": 245 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000488, - "loss": 5.3076, + "loss": 4.9583, "step": 246 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.00049, - "loss": 4.8769, + "loss": 5.7793, "step": 247 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000492, - "loss": 5.3764, + "loss": 5.4057, "step": 248 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000494, - "loss": 5.2015, + "loss": 5.7089, "step": 249 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000496, - "loss": 10.6736, + "loss": 4.8237, "step": 250 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000498, - "loss": 5.2372, + "loss": 5.4087, "step": 251 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.0005, - "loss": 7.5569, + "loss": 5.0223, "step": 252 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.0005020000000000001, - "loss": 6.1258, + "loss": 5.0797, "step": 253 }, { - "epoch": 0.14, + "epoch": 0.28, "learning_rate": 0.000504, - "loss": 5.5885, + "loss": 4.8901, "step": 254 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.000506, - "loss": 5.2723, + "loss": 5.1356, "step": 255 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.000508, - "loss": 5.2628, + "loss": 5.0586, "step": 256 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.00051, - "loss": 5.2784, + "loss": 5.1246, "step": 257 }, { - "epoch": 0.14, + "epoch": 0.29, "learning_rate": 0.000512, - "loss": 5.9104, + "loss": 4.8986, "step": 258 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.000514, - "loss": 5.4261, + "loss": 4.8121, "step": 259 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.0005160000000000001, - "loss": 4.9251, + "loss": 4.8494, "step": 260 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.000518, - "loss": 5.8871, + "loss": 4.8734, "step": 261 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.0005200000000000001, - "loss": 5.8142, + "loss": 4.9371, "step": 262 }, { - "epoch": 0.15, + "epoch": 0.29, "learning_rate": 0.000522, - "loss": 6.0686, + "loss": 4.7398, "step": 263 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.000524, - "loss": 5.6381, + "loss": 4.8513, "step": 264 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.000526, - "loss": 5.9545, + "loss": 5.242, "step": 265 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.000528, - "loss": 4.8176, + "loss": 5.0909, "step": 266 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.0005300000000000001, - "loss": 5.5368, + "loss": 5.0276, "step": 267 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.000532, - "loss": 5.9445, + "loss": 5.2137, "step": 268 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.0005340000000000001, - "loss": 5.2645, + "loss": 4.7544, "step": 269 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.000536, - "loss": 5.0683, + "loss": 5.0531, "step": 270 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.0005380000000000001, - "loss": 5.3492, + "loss": 4.7155, "step": 271 }, { - "epoch": 0.15, + "epoch": 0.3, "learning_rate": 0.00054, - "loss": 5.3108, + "loss": 4.9672, "step": 272 }, { - "epoch": 0.15, + "epoch": 0.31, "learning_rate": 0.0005420000000000001, - "loss": 4.8957, + "loss": 5.1118, "step": 273 }, { - "epoch": 0.15, + "epoch": 0.31, "learning_rate": 0.0005440000000000001, - "loss": 6.3335, + "loss": 4.766, "step": 274 }, { - "epoch": 0.15, + "epoch": 0.31, "learning_rate": 0.000546, - "loss": 6.2699, + "loss": 5.2889, "step": 275 }, { - "epoch": 0.15, + "epoch": 0.31, "learning_rate": 0.0005480000000000001, - "loss": 6.1695, + "loss": 5.2023, "step": 276 }, { - "epoch": 0.16, + "epoch": 0.31, "learning_rate": 0.00055, - "loss": 6.2355, + "loss": 4.9661, "step": 277 }, { - "epoch": 0.16, + "epoch": 0.31, "learning_rate": 0.0005520000000000001, - "loss": 5.4903, + "loss": 4.6719, "step": 278 }, { - "epoch": 0.16, + "epoch": 0.31, "learning_rate": 0.000554, - "loss": 5.0297, + "loss": 4.9073, "step": 279 }, { - "epoch": 0.16, + "epoch": 0.31, "learning_rate": 0.0005560000000000001, - "loss": 5.0909, + "loss": 5.0293, "step": 280 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.000558, - "loss": 5.8305, + "loss": 4.7573, "step": 281 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.0005600000000000001, - "loss": 5.6015, + "loss": 4.7975, "step": 282 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.0005620000000000001, - "loss": 6.5372, + "loss": 4.7992, "step": 283 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.0005639999999999999, - "loss": 5.0493, + "loss": 5.0759, "step": 284 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.000566, - "loss": 5.8203, + "loss": 5.1917, "step": 285 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.0005679999999999999, - "loss": 5.7623, + "loss": 4.9202, "step": 286 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.00057, - "loss": 5.391, + "loss": 5.34, "step": 287 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.0005719999999999999, - "loss": 5.4802, + "loss": 4.9242, "step": 288 }, { - "epoch": 0.16, + "epoch": 0.32, "learning_rate": 0.000574, - "loss": 5.0644, + "loss": 5.155, "step": 289 }, { - "epoch": 0.16, + "epoch": 0.33, "learning_rate": 0.000576, - "loss": 6.2312, + "loss": 5.1764, "step": 290 }, { - "epoch": 0.16, + "epoch": 0.33, "learning_rate": 0.000578, - "loss": 5.1057, + "loss": 4.9208, "step": 291 }, { - "epoch": 0.16, + "epoch": 0.33, "learning_rate": 0.00058, - "loss": 6.9815, + "loss": 4.7409, "step": 292 }, { - "epoch": 0.16, + "epoch": 0.33, "learning_rate": 0.0005819999999999999, - "loss": 5.3923, + "loss": 6.5954, "step": 293 }, { - "epoch": 0.16, + "epoch": 0.33, "learning_rate": 0.000584, - "loss": 5.4788, + "loss": 5.0484, "step": 294 }, { - "epoch": 0.17, + "epoch": 0.33, "learning_rate": 0.0005859999999999999, - "loss": 5.4079, + "loss": 4.7468, "step": 295 }, { - "epoch": 0.17, + "epoch": 0.33, "learning_rate": 0.000588, - "loss": 9.7116, + "loss": 5.7964, "step": 296 }, { - "epoch": 0.17, + "epoch": 0.33, "learning_rate": 0.00059, - "loss": 6.8535, + "loss": 5.9083, "step": 297 }, { - "epoch": 0.17, + "epoch": 0.33, "learning_rate": 0.000592, - "loss": 5.5679, + "loss": 5.1705, "step": 298 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000594, - "loss": 5.3228, + "loss": 5.4384, "step": 299 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000596, - "loss": 6.7207, + "loss": 5.4224, "step": 300 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000598, - "loss": 6.4039, + "loss": 5.329, "step": 301 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.0006, - "loss": 5.825, + "loss": 4.9936, "step": 302 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000602, - "loss": 5.6167, + "loss": 4.911, "step": 303 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000604, - "loss": 5.3904, + "loss": 4.9691, "step": 304 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000606, - "loss": 6.1199, + "loss": 5.0028, "step": 305 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.000608, - "loss": 5.5694, + "loss": 4.8037, "step": 306 }, { - "epoch": 0.17, + "epoch": 0.34, "learning_rate": 0.00061, - "loss": 5.5677, + "loss": 4.8418, "step": 307 }, { - "epoch": 0.17, + "epoch": 0.35, "learning_rate": 0.000612, - "loss": 7.9363, + "loss": 5.2496, "step": 308 }, { - "epoch": 0.17, + "epoch": 0.35, "learning_rate": 0.000614, - "loss": 5.4834, + "loss": 5.2615, "step": 309 }, { - "epoch": 0.17, + "epoch": 0.35, "learning_rate": 0.000616, - "loss": 6.2363, + "loss": 5.1208, "step": 310 }, { - "epoch": 0.17, + "epoch": 0.35, "learning_rate": 0.0006180000000000001, - "loss": 5.3806, + "loss": 5.1199, "step": 311 }, { - "epoch": 0.17, + "epoch": 0.35, "learning_rate": 0.00062, - "loss": 5.6296, + "loss": 4.9914, "step": 312 }, { - "epoch": 0.18, + "epoch": 0.35, "learning_rate": 0.000622, - "loss": 5.515, + "loss": 5.042, "step": 313 }, { - "epoch": 0.18, + "epoch": 0.35, "learning_rate": 0.000624, - "loss": 5.7467, + "loss": 4.9409, "step": 314 }, { - "epoch": 0.18, + "epoch": 0.35, "learning_rate": 0.000626, - "loss": 5.2309, + "loss": 4.8236, "step": 315 }, { - "epoch": 0.18, + "epoch": 0.35, "learning_rate": 0.000628, - "loss": 5.2063, + "loss": 5.1062, "step": 316 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.00063, - "loss": 5.1872, + "loss": 4.823, "step": 317 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.000632, - "loss": 5.1516, + "loss": 4.9081, "step": 318 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.000634, - "loss": 6.8123, + "loss": 4.8754, "step": 319 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.0006360000000000001, - "loss": 5.9006, + "loss": 4.8727, "step": 320 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.000638, - "loss": 6.2583, + "loss": 5.2652, "step": 321 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.00064, - "loss": 5.6284, + "loss": 4.7925, "step": 322 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.000642, - "loss": 5.6367, + "loss": 4.7254, "step": 323 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.000644, - "loss": 5.3076, + "loss": 5.2596, "step": 324 }, { - "epoch": 0.18, + "epoch": 0.36, "learning_rate": 0.000646, - "loss": 6.5229, + "loss": 5.1065, "step": 325 }, { - "epoch": 0.18, + "epoch": 0.37, "learning_rate": 0.000648, - "loss": 5.7701, + "loss": 5.0236, "step": 326 }, { - "epoch": 0.18, + "epoch": 0.37, "learning_rate": 0.0006500000000000001, - "loss": 5.9625, + "loss": 4.7007, "step": 327 }, { - "epoch": 0.18, + "epoch": 0.37, "learning_rate": 0.000652, - "loss": 6.1997, + "loss": 4.9706, "step": 328 }, { - "epoch": 0.18, + "epoch": 0.37, "learning_rate": 0.0006540000000000001, - "loss": 5.2808, + "loss": 5.3651, "step": 329 }, { - "epoch": 0.18, + "epoch": 0.37, "learning_rate": 0.000656, - "loss": 5.6101, + "loss": 5.3813, "step": 330 }, { - "epoch": 0.19, + "epoch": 0.37, "learning_rate": 0.0006580000000000001, - "loss": 5.4246, + "loss": 4.9263, "step": 331 }, { - "epoch": 0.19, + "epoch": 0.37, "learning_rate": 0.00066, - "loss": 6.2186, + "loss": 4.8357, "step": 332 }, { - "epoch": 0.19, + "epoch": 0.37, "learning_rate": 0.000662, - "loss": 6.6766, + "loss": 5.0999, "step": 333 }, { - "epoch": 0.19, + "epoch": 0.37, "learning_rate": 0.0006640000000000001, - "loss": 5.8022, + "loss": 5.017, "step": 334 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.000666, - "loss": 5.8503, + "loss": 5.0555, "step": 335 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.0006680000000000001, - "loss": 6.0338, + "loss": 5.0284, "step": 336 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.00067, - "loss": 5.3799, + "loss": 4.7011, "step": 337 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.0006720000000000001, - "loss": 5.4539, + "loss": 4.9937, "step": 338 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.000674, - "loss": 5.2275, + "loss": 4.9687, "step": 339 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.0006760000000000001, - "loss": 6.6346, + "loss": 4.8688, "step": 340 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.0006780000000000001, - "loss": 5.153, + "loss": 5.2171, "step": 341 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.00068, - "loss": 5.3877, + "loss": 4.9272, "step": 342 }, { - "epoch": 0.19, + "epoch": 0.38, "learning_rate": 0.0006820000000000001, - "loss": 5.4181, + "loss": 5.4399, "step": 343 }, { - "epoch": 0.19, + "epoch": 0.39, "learning_rate": 0.000684, - "loss": 5.1086, + "loss": 5.0394, "step": 344 }, { - "epoch": 0.19, + "epoch": 0.39, "learning_rate": 0.0006860000000000001, - "loss": 6.7033, + "loss": 4.89, "step": 345 }, { - "epoch": 0.19, + "epoch": 0.39, "learning_rate": 0.0006879999999999999, - "loss": 5.198, + "loss": 5.3467, "step": 346 }, { - "epoch": 0.19, + "epoch": 0.39, "learning_rate": 0.00069, - "loss": 5.9243, + "loss": 6.7675, "step": 347 }, { - "epoch": 0.2, + "epoch": 0.39, "learning_rate": 0.000692, - "loss": 5.5543, + "loss": 5.0929, "step": 348 }, { - "epoch": 0.2, + "epoch": 0.39, "learning_rate": 0.000694, - "loss": 5.9238, + "loss": 5.1975, "step": 349 }, { - "epoch": 0.2, + "epoch": 0.39, "learning_rate": 0.000696, - "loss": 5.2521, + "loss": 5.1623, "step": 350 }, { - "epoch": 0.2, + "epoch": 0.39, "learning_rate": 0.0006979999999999999, - "loss": 6.6807, + "loss": 5.7402, "step": 351 }, { - "epoch": 0.2, + "epoch": 0.39, "learning_rate": 0.0007, - "loss": 6.1464, + "loss": 5.0554, "step": 352 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.0007019999999999999, - "loss": 6.0735, + "loss": 5.1392, "step": 353 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.000704, - "loss": 5.6162, + "loss": 5.3242, "step": 354 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.0007059999999999999, - "loss": 5.3267, + "loss": 6.0127, "step": 355 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.000708, - "loss": 5.7805, + "loss": 5.3057, "step": 356 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.00071, - "loss": 5.6108, + "loss": 5.3195, "step": 357 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.000712, - "loss": 5.6875, + "loss": 5.2799, "step": 358 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.000714, - "loss": 7.0943, + "loss": 5.2069, "step": 359 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.000716, - "loss": 5.4442, + "loss": 5.1036, "step": 360 }, { - "epoch": 0.2, + "epoch": 0.4, "learning_rate": 0.000718, - "loss": 5.3216, + "loss": 5.2433, "step": 361 }, { - "epoch": 0.2, + "epoch": 0.41, "learning_rate": 0.0007199999999999999, - "loss": 4.9561, + "loss": 5.0837, "step": 362 }, { - "epoch": 0.2, + "epoch": 0.41, "learning_rate": 0.000722, - "loss": 5.5218, + "loss": 4.8481, "step": 363 }, { - "epoch": 0.2, + "epoch": 0.41, "learning_rate": 0.000724, - "loss": 5.9611, + "loss": 5.1938, "step": 364 }, { - "epoch": 0.2, + "epoch": 0.41, "learning_rate": 0.000726, - "loss": 6.5435, + "loss": 4.8737, "step": 365 }, { - "epoch": 0.21, + "epoch": 0.41, "learning_rate": 0.000728, - "loss": 6.2431, + "loss": 5.2159, "step": 366 }, { - "epoch": 0.21, + "epoch": 0.41, "learning_rate": 0.00073, - "loss": 5.6847, + "loss": 5.0045, "step": 367 }, { - "epoch": 0.21, + "epoch": 0.41, "learning_rate": 0.000732, - "loss": 5.6298, + "loss": 5.1269, "step": 368 }, { - "epoch": 0.21, + "epoch": 0.41, "learning_rate": 0.000734, - "loss": 6.6829, + "loss": 5.185, "step": 369 }, { - "epoch": 0.21, + "epoch": 0.41, "learning_rate": 0.000736, - "loss": 5.649, + "loss": 5.2436, "step": 370 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.000738, - "loss": 5.2472, + "loss": 4.9266, "step": 371 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.00074, - "loss": 5.9999, + "loss": 5.1939, "step": 372 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.000742, - "loss": 5.5913, + "loss": 5.1638, "step": 373 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.000744, - "loss": 5.8948, + "loss": 5.5325, "step": 374 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.000746, - "loss": 5.1289, + "loss": 4.8427, "step": 375 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.000748, - "loss": 5.5686, + "loss": 5.1271, "step": 376 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.00075, - "loss": 5.5028, + "loss": 4.8144, "step": 377 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.0007520000000000001, - "loss": 5.3661, + "loss": 5.1655, "step": 378 }, { - "epoch": 0.21, + "epoch": 0.42, "learning_rate": 0.000754, - "loss": 5.3831, + "loss": 4.9469, "step": 379 }, { - "epoch": 0.21, + "epoch": 0.43, "learning_rate": 0.000756, - "loss": 5.76, + "loss": 5.1108, "step": 380 }, { - "epoch": 0.21, + "epoch": 0.43, "learning_rate": 0.000758, - "loss": 5.2665, + "loss": 4.9925, "step": 381 }, { - "epoch": 0.21, + "epoch": 0.43, "learning_rate": 0.00076, - "loss": 5.3031, + "loss": 5.1714, "step": 382 }, { - "epoch": 0.21, + "epoch": 0.43, "learning_rate": 0.000762, - "loss": 5.3402, + "loss": 6.4374, "step": 383 }, { - "epoch": 0.22, + "epoch": 0.43, "learning_rate": 0.000764, - "loss": 6.8323, + "loss": 5.0459, "step": 384 }, { - "epoch": 0.22, + "epoch": 0.43, "learning_rate": 0.0007660000000000001, - "loss": 5.8042, + "loss": 4.9586, "step": 385 }, { - "epoch": 0.22, + "epoch": 0.43, "learning_rate": 0.000768, - "loss": 5.5112, + "loss": 5.0668, "step": 386 }, { - "epoch": 0.22, + "epoch": 0.43, "learning_rate": 0.0007700000000000001, - "loss": 6.4494, + "loss": 5.0477, "step": 387 }, { - "epoch": 0.22, + "epoch": 0.43, "learning_rate": 0.000772, - "loss": 5.0925, + "loss": 4.9241, "step": 388 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.0007740000000000001, - "loss": 5.6185, + "loss": 5.2005, "step": 389 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.000776, - "loss": 6.8436, + "loss": 5.6056, "step": 390 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.000778, - "loss": 5.0889, + "loss": 5.4428, "step": 391 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.0007800000000000001, - "loss": 6.0667, + "loss": 5.4239, "step": 392 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.000782, - "loss": 5.4234, + "loss": 5.3807, "step": 393 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.0007840000000000001, - "loss": 5.4818, + "loss": 5.2934, "step": 394 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.000786, - "loss": 5.9514, + "loss": 6.1639, "step": 395 }, { - "epoch": 0.22, + "epoch": 0.44, "learning_rate": 0.0007880000000000001, - "loss": 6.1241, + "loss": 5.2127, "step": 396 }, { - "epoch": 0.22, + "epoch": 0.45, "learning_rate": 0.00079, - "loss": 6.8583, + "loss": 6.2097, "step": 397 }, { - "epoch": 0.22, + "epoch": 0.45, "learning_rate": 0.0007920000000000001, - "loss": 6.9248, + "loss": 5.2827, "step": 398 }, { - "epoch": 0.22, + "epoch": 0.45, "learning_rate": 0.0007940000000000001, - "loss": 10.8678, + "loss": 5.1212, "step": 399 }, { - "epoch": 0.22, + "epoch": 0.45, "learning_rate": 0.000796, - "loss": 5.8768, + "loss": 5.472, "step": 400 }, { - "epoch": 0.22, + "epoch": 0.45, "learning_rate": 0.0007980000000000001, - "loss": 5.6533, + "loss": 5.4401, "step": 401 }, { - "epoch": 0.23, + "epoch": 0.45, "learning_rate": 0.0008, - "loss": 5.6349, + "loss": 5.2793, "step": 402 }, { - "epoch": 0.23, + "epoch": 0.45, "learning_rate": 0.0008020000000000001, - "loss": 5.6751, + "loss": 5.4463, "step": 403 }, { - "epoch": 0.23, + "epoch": 0.45, "learning_rate": 0.000804, - "loss": 5.8218, + "loss": 5.0944, "step": 404 }, { - "epoch": 0.23, + "epoch": 0.45, "learning_rate": 0.0008060000000000001, - "loss": 5.3772, + "loss": 5.3147, "step": 405 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.000808, - "loss": 6.1307, + "loss": 5.3533, "step": 406 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.0008100000000000001, - "loss": 5.962, + "loss": 5.163, "step": 407 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.0008120000000000001, - "loss": 5.3919, + "loss": 5.0185, "step": 408 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.0008139999999999999, - "loss": 5.9483, + "loss": 5.3798, "step": 409 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.000816, - "loss": 5.7156, + "loss": 5.3974, "step": 410 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.0008179999999999999, - "loss": 5.9583, + "loss": 5.0302, "step": 411 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.00082, - "loss": 5.5031, + "loss": 5.1526, "step": 412 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.0008219999999999999, - "loss": 6.3287, + "loss": 5.8772, "step": 413 }, { - "epoch": 0.23, + "epoch": 0.46, "learning_rate": 0.000824, - "loss": 5.6437, + "loss": 4.8392, "step": 414 }, { - "epoch": 0.23, + "epoch": 0.47, "learning_rate": 0.000826, - "loss": 6.5756, + "loss": 5.1069, "step": 415 }, { - "epoch": 0.23, + "epoch": 0.47, "learning_rate": 0.000828, - "loss": 5.4594, + "loss": 5.1643, "step": 416 }, { - "epoch": 0.23, + "epoch": 0.47, "learning_rate": 0.00083, - "loss": 6.3668, + "loss": 4.9795, "step": 417 }, { - "epoch": 0.23, + "epoch": 0.47, "learning_rate": 0.000832, - "loss": 5.8735, + "loss": 5.216, "step": 418 }, { - "epoch": 0.23, + "epoch": 0.47, "learning_rate": 0.000834, - "loss": 5.57, + "loss": 5.0386, "step": 419 }, { - "epoch": 0.24, + "epoch": 0.47, "learning_rate": 0.0008359999999999999, - "loss": 5.6743, + "loss": 5.0863, "step": 420 }, { - "epoch": 0.24, + "epoch": 0.47, "learning_rate": 0.000838, - "loss": 5.4278, + "loss": 4.9586, "step": 421 }, { - "epoch": 0.24, + "epoch": 0.47, "learning_rate": 0.00084, - "loss": 5.8436, + "loss": 5.2313, "step": 422 }, { - "epoch": 0.24, + "epoch": 0.47, "learning_rate": 0.000842, - "loss": 5.3494, + "loss": 6.1135, "step": 423 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000844, - "loss": 5.9252, + "loss": 5.0778, "step": 424 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000846, - "loss": 5.5169, + "loss": 5.1118, "step": 425 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000848, - "loss": 5.4256, + "loss": 5.2043, "step": 426 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.00085, - "loss": 5.98, + "loss": 4.9702, "step": 427 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000852, - "loss": 6.5838, + "loss": 5.3167, "step": 428 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000854, - "loss": 5.7028, + "loss": 4.9597, "step": 429 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000856, - "loss": 5.5075, + "loss": 5.115, "step": 430 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.000858, - "loss": 6.0355, + "loss": 5.4418, "step": 431 }, { - "epoch": 0.24, + "epoch": 0.48, "learning_rate": 0.00086, - "loss": 5.4179, + "loss": 5.1764, "step": 432 }, { - "epoch": 0.24, + "epoch": 0.49, "learning_rate": 0.000862, - "loss": 5.6191, + "loss": 4.8251, "step": 433 }, { - "epoch": 0.24, + "epoch": 0.49, "learning_rate": 0.000864, - "loss": 5.685, + "loss": 5.2088, "step": 434 }, { - "epoch": 0.24, + "epoch": 0.49, "learning_rate": 0.000866, - "loss": 5.4582, + "loss": 5.0211, "step": 435 }, { - "epoch": 0.24, + "epoch": 0.49, "learning_rate": 0.0008680000000000001, - "loss": 5.7428, + "loss": 5.2176, "step": 436 }, { - "epoch": 0.24, + "epoch": 0.49, "learning_rate": 0.00087, - "loss": 5.512, + "loss": 5.2249, "step": 437 }, { - "epoch": 0.25, + "epoch": 0.49, "learning_rate": 0.000872, - "loss": 5.5949, + "loss": 5.118, "step": 438 }, { - "epoch": 0.25, + "epoch": 0.49, "learning_rate": 0.000874, - "loss": 5.2282, + "loss": 5.1533, "step": 439 }, { - "epoch": 0.25, + "epoch": 0.49, "learning_rate": 0.000876, - "loss": 5.5467, + "loss": 5.0237, "step": 440 }, { - "epoch": 0.25, + "epoch": 0.49, "learning_rate": 0.000878, - "loss": 5.9093, + "loss": 5.3436, "step": 441 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.00088, - "loss": 7.4039, + "loss": 4.9092, "step": 442 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.000882, - "loss": 5.4882, + "loss": 5.0294, "step": 443 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.000884, - "loss": 5.8418, + "loss": 5.5218, "step": 444 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.0008860000000000001, - "loss": 5.5112, + "loss": 4.9374, "step": 445 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.000888, - "loss": 8.8027, + "loss": 4.821, "step": 446 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.0008900000000000001, - "loss": 7.1436, + "loss": 4.9246, "step": 447 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.000892, - "loss": 6.0517, + "loss": 7.544, "step": 448 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.000894, - "loss": 6.747, + "loss": 6.0168, "step": 449 }, { - "epoch": 0.25, + "epoch": 0.5, "learning_rate": 0.000896, - "loss": 6.6775, + "loss": 7.3071, "step": 450 }, { - "epoch": 0.25, + "epoch": 0.51, "learning_rate": 0.000898, - "loss": 5.6388, + "loss": 5.3956, "step": 451 }, { - "epoch": 0.25, + "epoch": 0.51, "learning_rate": 0.0009000000000000001, - "loss": 5.8886, + "loss": 5.48, "step": 452 }, { - "epoch": 0.25, + "epoch": 0.51, "learning_rate": 0.000902, - "loss": 6.934, + "loss": 5.4334, "step": 453 }, { - "epoch": 0.25, + "epoch": 0.51, "learning_rate": 0.0009040000000000001, - "loss": 5.5421, + "loss": 5.0337, "step": 454 }, { - "epoch": 0.26, + "epoch": 0.51, "learning_rate": 0.000906, - "loss": 5.5831, + "loss": 5.4256, "step": 455 }, { - "epoch": 0.26, + "epoch": 0.51, "learning_rate": 0.0009080000000000001, - "loss": 5.6598, + "loss": 5.3247, "step": 456 }, { - "epoch": 0.26, + "epoch": 0.51, "learning_rate": 0.00091, - "loss": 6.0166, + "loss": 5.2336, "step": 457 }, { - "epoch": 0.26, + "epoch": 0.51, "learning_rate": 0.000912, - "loss": 5.5779, + "loss": 5.3589, "step": 458 }, { - "epoch": 0.26, + "epoch": 0.51, "learning_rate": 0.0009140000000000001, - "loss": 5.4935, + "loss": 5.2095, "step": 459 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.000916, - "loss": 5.704, + "loss": 5.3384, "step": 460 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.0009180000000000001, - "loss": 7.7115, + "loss": 4.9632, "step": 461 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.00092, - "loss": 5.3225, + "loss": 5.3328, "step": 462 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.0009220000000000001, - "loss": 5.9773, + "loss": 5.5567, "step": 463 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.000924, - "loss": 7.1143, + "loss": 4.9068, "step": 464 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.0009260000000000001, - "loss": 6.67, + "loss": 5.1143, "step": 465 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.0009280000000000001, - "loss": 6.6142, + "loss": 5.3116, "step": 466 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.00093, - "loss": 5.91, + "loss": 5.0797, "step": 467 }, { - "epoch": 0.26, + "epoch": 0.52, "learning_rate": 0.0009320000000000001, - "loss": 6.3521, + "loss": 5.1186, "step": 468 }, { - "epoch": 0.26, + "epoch": 0.53, "learning_rate": 0.000934, - "loss": 5.3542, + "loss": 5.4416, "step": 469 }, { - "epoch": 0.26, + "epoch": 0.53, "learning_rate": 0.0009360000000000001, - "loss": 5.8032, + "loss": 5.1664, "step": 470 }, { - "epoch": 0.26, + "epoch": 0.53, "learning_rate": 0.0009379999999999999, - "loss": 6.0444, + "loss": 4.9481, "step": 471 }, { - "epoch": 0.26, + "epoch": 0.53, "learning_rate": 0.00094, - "loss": 5.4191, + "loss": 4.9097, "step": 472 }, { - "epoch": 0.27, + "epoch": 0.53, "learning_rate": 0.000942, - "loss": 5.3476, + "loss": 5.6217, "step": 473 }, { - "epoch": 0.27, + "epoch": 0.53, "learning_rate": 0.000944, - "loss": 6.6918, + "loss": 5.1009, "step": 474 }, { - "epoch": 0.27, + "epoch": 0.53, "learning_rate": 0.000946, - "loss": 5.6161, + "loss": 5.3705, "step": 475 }, { - "epoch": 0.27, + "epoch": 0.53, "learning_rate": 0.000948, - "loss": 5.6343, + "loss": 5.418, "step": 476 }, { - "epoch": 0.27, + "epoch": 0.53, "learning_rate": 0.00095, - "loss": 5.776, + "loss": 5.5494, "step": 477 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.0009519999999999999, - "loss": 5.4862, + "loss": 5.0258, "step": 478 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.000954, - "loss": 5.8037, + "loss": 5.0919, "step": 479 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.0009559999999999999, - "loss": 6.1862, + "loss": 5.0294, "step": 480 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.000958, - "loss": 5.6293, + "loss": 5.0032, "step": 481 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.00096, - "loss": 6.6196, + "loss": 5.3622, "step": 482 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.000962, - "loss": 6.0316, + "loss": 5.016, "step": 483 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.000964, - "loss": 5.5718, + "loss": 5.3424, "step": 484 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.000966, - "loss": 5.9355, + "loss": 5.3396, "step": 485 }, { - "epoch": 0.27, + "epoch": 0.54, "learning_rate": 0.000968, - "loss": 5.9243, + "loss": 4.9877, "step": 486 }, { - "epoch": 0.27, + "epoch": 0.55, "learning_rate": 0.0009699999999999999, - "loss": 5.478, + "loss": 5.0559, "step": 487 }, { - "epoch": 0.27, + "epoch": 0.55, "learning_rate": 0.000972, - "loss": 5.9595, + "loss": 4.8909, "step": 488 }, { - "epoch": 0.27, + "epoch": 0.55, "learning_rate": 0.000974, - "loss": 5.7734, + "loss": 5.3144, "step": 489 }, { - "epoch": 0.27, + "epoch": 0.55, "learning_rate": 0.000976, - "loss": 5.5472, + "loss": 5.2026, "step": 490 }, { - "epoch": 0.28, + "epoch": 0.55, "learning_rate": 0.000978, - "loss": 5.2288, + "loss": 4.904, "step": 491 }, { - "epoch": 0.28, + "epoch": 0.55, "learning_rate": 0.00098, - "loss": 6.0956, + "loss": 5.5084, "step": 492 }, { - "epoch": 0.28, + "epoch": 0.55, "learning_rate": 0.000982, - "loss": 6.6603, + "loss": 5.2827, "step": 493 }, { - "epoch": 0.28, + "epoch": 0.55, "learning_rate": 0.000984, - "loss": 6.5782, + "loss": 5.1398, "step": 494 }, { - "epoch": 0.28, + "epoch": 0.55, "learning_rate": 0.0009860000000000001, - "loss": 6.5649, + "loss": 5.5595, "step": 495 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.000988, - "loss": 5.5781, + "loss": 4.8808, "step": 496 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.00099, - "loss": 5.6801, + "loss": 4.8302, "step": 497 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.000992, - "loss": 7.0006, + "loss": 5.6899, "step": 498 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.000994, - "loss": 5.8138, + "loss": 5.4486, "step": 499 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.000996, - "loss": 5.4548, + "loss": 4.7246, "step": 500 }, { - "epoch": 0.28, - "eval_loss": 5.980778694152832, - "eval_runtime": 972.2623, - "eval_samples_per_second": 2.717, - "eval_steps_per_second": 0.34, - "eval_wer": 1.7240975803252678, + "epoch": 0.56, + "eval_loss": 5.553798675537109, + "eval_runtime": 947.3214, + "eval_samples_per_second": 2.789, + "eval_steps_per_second": 0.349, + "eval_wer": 2.01330821102737, "step": 500 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.000998, - "loss": 6.4359, + "loss": 6.2615, "step": 501 }, { - "epoch": 0.28, + "epoch": 0.56, "learning_rate": 0.001, - "loss": 5.6392, + "loss": 4.9686, "step": 502 }, { - "epoch": 0.28, - "learning_rate": 0.0009992211838006232, - "loss": 5.8528, + "epoch": 0.56, + "learning_rate": 0.0009974489795918369, + "loss": 5.2496, "step": 503 }, { - "epoch": 0.28, - "learning_rate": 0.000998442367601246, - "loss": 5.6225, + "epoch": 0.57, + "learning_rate": 0.0009948979591836735, + "loss": 5.4162, "step": 504 }, { - "epoch": 0.28, - "learning_rate": 0.0009976635514018692, - "loss": 6.4764, + "epoch": 0.57, + "learning_rate": 0.00099234693877551, + "loss": 5.3041, "step": 505 }, { - "epoch": 0.28, - "learning_rate": 0.0009968847352024922, - "loss": 6.1976, + "epoch": 0.57, + "learning_rate": 0.000989795918367347, + "loss": 5.2386, "step": 506 }, { - "epoch": 0.28, - "learning_rate": 0.0009961059190031153, - "loss": 5.5245, + "epoch": 0.57, + "learning_rate": 0.0009872448979591838, + "loss": 5.3472, "step": 507 }, { - "epoch": 0.28, - "learning_rate": 0.0009953271028037385, - "loss": 5.641, + "epoch": 0.57, + "learning_rate": 0.0009846938775510204, + "loss": 5.1626, "step": 508 }, { - "epoch": 0.29, - "learning_rate": 0.0009945482866043614, - "loss": 7.22, + "epoch": 0.57, + "learning_rate": 0.0009821428571428572, + "loss": 5.3774, "step": 509 }, { - "epoch": 0.29, - "learning_rate": 0.0009937694704049845, - "loss": 6.0472, + "epoch": 0.57, + "learning_rate": 0.0009795918367346938, + "loss": 5.6755, "step": 510 }, { - "epoch": 0.29, - "learning_rate": 0.0009929906542056075, - "loss": 5.6482, + "epoch": 0.57, + "learning_rate": 0.0009770408163265307, + "loss": 5.1559, "step": 511 }, { - "epoch": 0.29, - "learning_rate": 0.0009922118380062306, - "loss": 6.8253, + "epoch": 0.57, + "learning_rate": 0.0009744897959183674, + "loss": 5.0161, "step": 512 }, { - "epoch": 0.29, - "learning_rate": 0.0009914330218068535, - "loss": 6.023, + "epoch": 0.58, + "learning_rate": 0.0009719387755102041, + "loss": 5.6675, "step": 513 }, { - "epoch": 0.29, - "learning_rate": 0.0009906542056074767, - "loss": 5.304, + "epoch": 0.58, + "learning_rate": 0.0009693877551020408, + "loss": 5.1173, "step": 514 }, { - "epoch": 0.29, - "learning_rate": 0.0009898753894080998, - "loss": 5.45, + "epoch": 0.58, + "learning_rate": 0.0009668367346938776, + "loss": 5.2748, "step": 515 }, { - "epoch": 0.29, - "learning_rate": 0.0009890965732087227, - "loss": 7.5223, + "epoch": 0.58, + "learning_rate": 0.0009642857142857143, + "loss": 5.033, "step": 516 }, { - "epoch": 0.29, - "learning_rate": 0.000988317757009346, - "loss": 6.3873, + "epoch": 0.58, + "learning_rate": 0.0009617346938775511, + "loss": 5.2472, "step": 517 }, { - "epoch": 0.29, - "learning_rate": 0.0009875389408099688, - "loss": 5.6919, + "epoch": 0.58, + "learning_rate": 0.0009591836734693877, + "loss": 5.1146, "step": 518 }, { - "epoch": 0.29, - "learning_rate": 0.000986760124610592, - "loss": 5.8967, + "epoch": 0.58, + "learning_rate": 0.0009566326530612245, + "loss": 5.4533, "step": 519 }, { - "epoch": 0.29, - "learning_rate": 0.0009859813084112151, - "loss": 6.0559, + "epoch": 0.58, + "learning_rate": 0.0009540816326530613, + "loss": 5.4604, "step": 520 }, { - "epoch": 0.29, - "learning_rate": 0.000985202492211838, - "loss": 5.3471, + "epoch": 0.58, + "learning_rate": 0.000951530612244898, + "loss": 5.3102, "step": 521 }, { - "epoch": 0.29, - "learning_rate": 0.0009844236760124612, - "loss": 5.9164, + "epoch": 0.59, + "learning_rate": 0.0009489795918367348, + "loss": 5.0594, "step": 522 }, { - "epoch": 0.29, - "learning_rate": 0.0009836448598130841, - "loss": 6.2262, + "epoch": 0.59, + "learning_rate": 0.0009464285714285714, + "loss": 5.3375, "step": 523 }, { - "epoch": 0.29, - "learning_rate": 0.0009828660436137073, - "loss": 5.9193, + "epoch": 0.59, + "learning_rate": 0.0009438775510204082, + "loss": 5.2176, "step": 524 }, { - "epoch": 0.29, - "learning_rate": 0.0009820872274143302, - "loss": 7.292, + "epoch": 0.59, + "learning_rate": 0.0009413265306122449, + "loss": 5.9862, "step": 525 }, { - "epoch": 0.29, - "learning_rate": 0.0009813084112149533, - "loss": 5.493, + "epoch": 0.59, + "learning_rate": 0.0009387755102040817, + "loss": 5.0509, "step": 526 }, { - "epoch": 0.3, - "learning_rate": 0.0009805295950155765, - "loss": 6.264, + "epoch": 0.59, + "learning_rate": 0.0009362244897959184, + "loss": 5.1616, "step": 527 }, { - "epoch": 0.3, - "learning_rate": 0.0009797507788161994, - "loss": 5.7357, + "epoch": 0.59, + "learning_rate": 0.0009336734693877551, + "loss": 5.1956, "step": 528 }, { - "epoch": 0.3, - "learning_rate": 0.0009789719626168223, - "loss": 6.0991, + "epoch": 0.59, + "learning_rate": 0.0009311224489795918, + "loss": 5.795, "step": 529 }, { - "epoch": 0.3, - "learning_rate": 0.0009781931464174455, - "loss": 7.0431, + "epoch": 0.59, + "learning_rate": 0.0009285714285714287, + "loss": 5.4817, "step": 530 }, { - "epoch": 0.3, - "learning_rate": 0.0009774143302180686, - "loss": 5.4246, + "epoch": 0.6, + "learning_rate": 0.0009260204081632653, + "loss": 5.6069, "step": 531 }, { - "epoch": 0.3, - "learning_rate": 0.0009766355140186918, - "loss": 5.402, + "epoch": 0.6, + "learning_rate": 0.000923469387755102, + "loss": 4.8953, "step": 532 }, { - "epoch": 0.3, - "learning_rate": 0.0009758566978193146, - "loss": 5.9838, + "epoch": 0.6, + "learning_rate": 0.0009209183673469387, + "loss": 4.9381, "step": 533 }, { - "epoch": 0.3, - "learning_rate": 0.0009750778816199377, - "loss": 5.372, + "epoch": 0.6, + "learning_rate": 0.0009183673469387756, + "loss": 4.9541, "step": 534 }, { - "epoch": 0.3, - "learning_rate": 0.0009742990654205608, - "loss": 5.9725, + "epoch": 0.6, + "learning_rate": 0.0009158163265306123, + "loss": 5.0257, "step": 535 }, { - "epoch": 0.3, - "learning_rate": 0.0009735202492211839, - "loss": 5.6769, + "epoch": 0.6, + "learning_rate": 0.0009132653061224489, + "loss": 5.4078, "step": 536 }, { - "epoch": 0.3, - "learning_rate": 0.0009727414330218068, - "loss": 5.3817, + "epoch": 0.6, + "learning_rate": 0.0009107142857142857, + "loss": 5.3974, "step": 537 }, { - "epoch": 0.3, - "learning_rate": 0.0009719626168224299, - "loss": 6.3551, + "epoch": 0.6, + "learning_rate": 0.0009081632653061225, + "loss": 5.3991, "step": 538 }, { - "epoch": 0.3, - "learning_rate": 0.000971183800623053, - "loss": 5.673, + "epoch": 0.6, + "learning_rate": 0.0009056122448979592, + "loss": 5.2251, "step": 539 }, { - "epoch": 0.3, - "learning_rate": 0.0009704049844236761, - "loss": 5.687, + "epoch": 0.61, + "learning_rate": 0.0009030612244897959, + "loss": 5.3175, "step": 540 }, { - "epoch": 0.3, - "learning_rate": 0.0009696261682242991, - "loss": 5.6295, + "epoch": 0.61, + "learning_rate": 0.0009005102040816327, + "loss": 5.361, "step": 541 }, { - "epoch": 0.3, - "learning_rate": 0.0009688473520249221, - "loss": 5.7054, + "epoch": 0.61, + "learning_rate": 0.0008979591836734694, + "loss": 5.3854, "step": 542 }, { - "epoch": 0.3, - "learning_rate": 0.0009680685358255452, - "loss": 7.7628, + "epoch": 0.61, + "learning_rate": 0.0008954081632653062, + "loss": 5.2583, "step": 543 }, { - "epoch": 0.3, - "learning_rate": 0.0009672897196261683, - "loss": 5.7015, + "epoch": 0.61, + "learning_rate": 0.0008928571428571429, + "loss": 5.4731, "step": 544 }, { - "epoch": 0.31, - "learning_rate": 0.0009665109034267912, - "loss": 5.5604, + "epoch": 0.61, + "learning_rate": 0.0008903061224489796, + "loss": 6.1977, "step": 545 }, { - "epoch": 0.31, - "learning_rate": 0.0009657320872274144, - "loss": 7.7083, + "epoch": 0.61, + "learning_rate": 0.0008877551020408163, + "loss": 5.2304, "step": 546 }, { - "epoch": 0.31, - "learning_rate": 0.0009649532710280374, - "loss": 6.4384, + "epoch": 0.61, + "learning_rate": 0.0008852040816326531, + "loss": 5.8843, "step": 547 }, { - "epoch": 0.31, - "learning_rate": 0.0009641744548286605, - "loss": 6.7681, + "epoch": 0.61, + "learning_rate": 0.0008826530612244898, + "loss": 5.4071, "step": 548 }, { - "epoch": 0.31, - "learning_rate": 0.0009633956386292835, - "loss": 6.4208, + "epoch": 0.62, + "learning_rate": 0.0008801020408163265, + "loss": 5.0849, "step": 549 }, { - "epoch": 0.31, - "learning_rate": 0.0009626168224299065, - "loss": 5.5422, + "epoch": 0.62, + "learning_rate": 0.0008775510204081633, + "loss": 5.8482, "step": 550 }, { - "epoch": 0.31, - "learning_rate": 0.0009618380062305297, - "loss": 7.2491, + "epoch": 0.62, + "learning_rate": 0.000875, + "loss": 5.2635, "step": 551 }, { - "epoch": 0.31, - "learning_rate": 0.0009610591900311527, - "loss": 7.1051, + "epoch": 0.62, + "learning_rate": 0.0008724489795918367, + "loss": 5.418, "step": 552 }, { - "epoch": 0.31, - "learning_rate": 0.0009602803738317756, - "loss": 6.6283, + "epoch": 0.62, + "learning_rate": 0.0008698979591836736, + "loss": 5.2408, "step": 553 }, { - "epoch": 0.31, - "learning_rate": 0.0009595015576323988, - "loss": 5.7891, + "epoch": 0.62, + "learning_rate": 0.0008673469387755102, + "loss": 5.0475, "step": 554 }, { - "epoch": 0.31, - "learning_rate": 0.0009587227414330218, - "loss": 5.9882, + "epoch": 0.62, + "learning_rate": 0.0008647959183673469, + "loss": 5.0966, "step": 555 }, { - "epoch": 0.31, - "learning_rate": 0.000957943925233645, - "loss": 6.1033, + "epoch": 0.62, + "learning_rate": 0.0008622448979591838, + "loss": 5.0922, "step": 556 }, { - "epoch": 0.31, - "learning_rate": 0.0009571651090342679, - "loss": 6.1674, + "epoch": 0.62, + "learning_rate": 0.0008596938775510205, + "loss": 4.9667, "step": 557 }, { - "epoch": 0.31, - "learning_rate": 0.000956386292834891, - "loss": 5.6939, + "epoch": 0.63, + "learning_rate": 0.0008571428571428571, + "loss": 5.2674, "step": 558 }, { - "epoch": 0.31, - "learning_rate": 0.0009556074766355141, - "loss": 5.4137, + "epoch": 0.63, + "learning_rate": 0.0008545918367346938, + "loss": 5.0393, "step": 559 }, { - "epoch": 0.31, - "learning_rate": 0.0009548286604361371, - "loss": 5.5022, + "epoch": 0.63, + "learning_rate": 0.0008520408163265307, + "loss": 5.0971, "step": 560 }, { - "epoch": 0.31, - "learning_rate": 0.0009540498442367601, - "loss": 5.7693, + "epoch": 0.63, + "learning_rate": 0.0008494897959183674, + "loss": 5.1893, "step": 561 }, { - "epoch": 0.32, - "learning_rate": 0.0009532710280373832, - "loss": 5.8362, + "epoch": 0.63, + "learning_rate": 0.0008469387755102041, + "loss": 5.0583, "step": 562 }, { - "epoch": 0.32, - "learning_rate": 0.0009524922118380063, - "loss": 5.4616, + "epoch": 0.63, + "learning_rate": 0.0008443877551020408, + "loss": 5.1257, "step": 563 }, { - "epoch": 0.32, - "learning_rate": 0.0009517133956386294, - "loss": 5.8008, + "epoch": 0.63, + "learning_rate": 0.0008418367346938776, + "loss": 5.0834, "step": 564 }, { - "epoch": 0.32, - "learning_rate": 0.0009509345794392523, - "loss": 6.1251, + "epoch": 0.63, + "learning_rate": 0.0008392857142857143, + "loss": 5.148, "step": 565 }, { - "epoch": 0.32, - "learning_rate": 0.0009501557632398754, - "loss": 5.3255, + "epoch": 0.63, + "learning_rate": 0.0008367346938775511, + "loss": 5.06, "step": 566 }, { - "epoch": 0.32, - "learning_rate": 0.0009493769470404985, - "loss": 5.6258, + "epoch": 0.64, + "learning_rate": 0.0008341836734693877, + "loss": 5.0448, "step": 567 }, { - "epoch": 0.32, - "learning_rate": 0.0009485981308411216, - "loss": 6.0075, + "epoch": 0.64, + "learning_rate": 0.0008316326530612245, + "loss": 4.8972, "step": 568 }, { - "epoch": 0.32, - "learning_rate": 0.0009478193146417445, - "loss": 5.6322, + "epoch": 0.64, + "learning_rate": 0.0008290816326530613, + "loss": 4.9932, "step": 569 }, { - "epoch": 0.32, - "learning_rate": 0.0009470404984423676, - "loss": 5.6237, + "epoch": 0.64, + "learning_rate": 0.000826530612244898, + "loss": 5.1723, "step": 570 }, { - "epoch": 0.32, - "learning_rate": 0.0009462616822429907, - "loss": 5.9168, + "epoch": 0.64, + "learning_rate": 0.0008239795918367348, + "loss": 4.9847, "step": 571 }, { - "epoch": 0.32, - "learning_rate": 0.0009454828660436138, - "loss": 5.6341, + "epoch": 0.64, + "learning_rate": 0.0008214285714285714, + "loss": 5.0464, "step": 572 }, { - "epoch": 0.32, - "learning_rate": 0.0009447040498442368, - "loss": 6.4811, + "epoch": 0.64, + "learning_rate": 0.0008188775510204082, + "loss": 5.0259, "step": 573 }, { - "epoch": 0.32, - "learning_rate": 0.0009439252336448598, - "loss": 5.2509, + "epoch": 0.64, + "learning_rate": 0.0008163265306122449, + "loss": 5.5426, "step": 574 }, { - "epoch": 0.32, - "learning_rate": 0.0009431464174454829, - "loss": 5.3237, + "epoch": 0.64, + "learning_rate": 0.0008137755102040817, + "loss": 5.3417, "step": 575 }, { - "epoch": 0.32, - "learning_rate": 0.000942367601246106, - "loss": 5.3686, + "epoch": 0.65, + "learning_rate": 0.0008112244897959184, + "loss": 5.0017, "step": 576 }, { - "epoch": 0.32, - "learning_rate": 0.0009415887850467289, - "loss": 5.4865, + "epoch": 0.65, + "learning_rate": 0.0008086734693877551, + "loss": 5.0695, "step": 577 }, { - "epoch": 0.32, - "learning_rate": 0.0009408099688473521, - "loss": 5.2369, + "epoch": 0.65, + "learning_rate": 0.0008061224489795918, + "loss": 5.1576, "step": 578 }, { - "epoch": 0.32, - "learning_rate": 0.0009400311526479751, - "loss": 5.6395, + "epoch": 0.65, + "learning_rate": 0.0008035714285714287, + "loss": 4.7052, "step": 579 }, { - "epoch": 0.33, - "learning_rate": 0.0009392523364485982, - "loss": 6.0003, + "epoch": 0.65, + "learning_rate": 0.0008010204081632653, + "loss": 5.4356, "step": 580 }, { - "epoch": 0.33, - "learning_rate": 0.0009384735202492212, - "loss": 5.4733, + "epoch": 0.65, + "learning_rate": 0.000798469387755102, + "loss": 5.1405, "step": 581 }, { - "epoch": 0.33, - "learning_rate": 0.0009376947040498442, - "loss": 5.5697, + "epoch": 0.65, + "learning_rate": 0.0007959183673469387, + "loss": 4.9729, "step": 582 }, { - "epoch": 0.33, - "learning_rate": 0.0009369158878504674, - "loss": 5.8127, + "epoch": 0.65, + "learning_rate": 0.0007933673469387756, + "loss": 5.4895, "step": 583 }, { - "epoch": 0.33, - "learning_rate": 0.0009361370716510904, - "loss": 5.9106, + "epoch": 0.65, + "learning_rate": 0.0007908163265306123, + "loss": 5.0296, "step": 584 }, { - "epoch": 0.33, - "learning_rate": 0.0009353582554517133, - "loss": 6.7359, + "epoch": 0.66, + "learning_rate": 0.0007882653061224489, + "loss": 5.7285, "step": 585 }, { - "epoch": 0.33, - "learning_rate": 0.0009345794392523365, - "loss": 5.2045, + "epoch": 0.66, + "learning_rate": 0.0007857142857142857, + "loss": 5.4251, "step": 586 }, { - "epoch": 0.33, - "learning_rate": 0.0009338006230529595, - "loss": 6.0086, + "epoch": 0.66, + "learning_rate": 0.0007831632653061225, + "loss": 5.603, "step": 587 }, { - "epoch": 0.33, - "learning_rate": 0.0009330218068535827, - "loss": 5.5215, + "epoch": 0.66, + "learning_rate": 0.0007806122448979592, + "loss": 4.9566, "step": 588 }, { - "epoch": 0.33, - "learning_rate": 0.0009322429906542056, - "loss": 5.8927, + "epoch": 0.66, + "learning_rate": 0.0007780612244897959, + "loss": 4.9453, "step": 589 }, { - "epoch": 0.33, - "learning_rate": 0.0009314641744548286, - "loss": 6.0077, + "epoch": 0.66, + "learning_rate": 0.0007755102040816326, + "loss": 5.4635, "step": 590 }, { - "epoch": 0.33, - "learning_rate": 0.0009306853582554518, - "loss": 5.5207, + "epoch": 0.66, + "learning_rate": 0.0007729591836734694, + "loss": 5.0545, "step": 591 }, { - "epoch": 0.33, - "learning_rate": 0.0009299065420560748, - "loss": 5.5035, + "epoch": 0.66, + "learning_rate": 0.0007704081632653062, + "loss": 5.6657, "step": 592 }, { - "epoch": 0.33, - "learning_rate": 0.0009291277258566979, - "loss": 5.3549, + "epoch": 0.66, + "learning_rate": 0.0007678571428571429, + "loss": 5.4611, "step": 593 }, { - "epoch": 0.33, - "learning_rate": 0.0009283489096573209, - "loss": 5.6618, + "epoch": 0.67, + "learning_rate": 0.0007653061224489796, + "loss": 4.968, "step": 594 }, { - "epoch": 0.33, - "learning_rate": 0.0009275700934579439, - "loss": 5.4131, + "epoch": 0.67, + "learning_rate": 0.0007627551020408163, + "loss": 5.477, "step": 595 }, { - "epoch": 0.33, - "learning_rate": 0.0009267912772585671, - "loss": 5.4942, + "epoch": 0.67, + "learning_rate": 0.0007602040816326531, + "loss": 5.3628, "step": 596 }, { - "epoch": 0.33, - "learning_rate": 0.00092601246105919, - "loss": 10.3257, + "epoch": 0.67, + "learning_rate": 0.0007576530612244898, + "loss": 5.1578, "step": 597 }, { - "epoch": 0.34, - "learning_rate": 0.0009252336448598131, - "loss": 7.6016, + "epoch": 0.67, + "learning_rate": 0.0007551020408163265, + "loss": 5.3148, "step": 598 }, { - "epoch": 0.34, - "learning_rate": 0.0009244548286604362, - "loss": 5.704, + "epoch": 0.67, + "learning_rate": 0.0007525510204081633, + "loss": 5.5493, "step": 599 }, { - "epoch": 0.34, - "learning_rate": 0.0009236760124610592, - "loss": 5.8385, + "epoch": 0.67, + "learning_rate": 0.00075, + "loss": 4.9865, "step": 600 }, { - "epoch": 0.34, - "learning_rate": 0.0009228971962616823, - "loss": 5.438, + "epoch": 0.67, + "learning_rate": 0.0007474489795918367, + "loss": 5.2224, "step": 601 }, { - "epoch": 0.34, - "learning_rate": 0.0009221183800623053, - "loss": 5.6865, + "epoch": 0.67, + "learning_rate": 0.0007448979591836736, + "loss": 5.1809, "step": 602 }, { - "epoch": 0.34, - "learning_rate": 0.0009213395638629284, - "loss": 5.9924, + "epoch": 0.68, + "learning_rate": 0.0007423469387755102, + "loss": 5.2736, "step": 603 }, { - "epoch": 0.34, - "learning_rate": 0.0009205607476635515, - "loss": 5.5931, + "epoch": 0.68, + "learning_rate": 0.0007397959183673469, + "loss": 5.1739, "step": 604 }, { - "epoch": 0.34, - "learning_rate": 0.0009197819314641744, - "loss": 5.729, + "epoch": 0.68, + "learning_rate": 0.0007372448979591838, + "loss": 5.0983, "step": 605 }, { - "epoch": 0.34, - "learning_rate": 0.0009190031152647975, - "loss": 5.3185, + "epoch": 0.68, + "learning_rate": 0.0007346938775510205, + "loss": 4.9385, "step": 606 }, { - "epoch": 0.34, - "learning_rate": 0.0009182242990654206, - "loss": 6.1185, + "epoch": 0.68, + "learning_rate": 0.0007321428571428571, + "loss": 5.867, "step": 607 }, { - "epoch": 0.34, - "learning_rate": 0.0009174454828660437, - "loss": 6.1975, + "epoch": 0.68, + "learning_rate": 0.0007295918367346938, + "loss": 5.0564, "step": 608 }, { - "epoch": 0.34, - "learning_rate": 0.0009166666666666666, - "loss": 6.2431, + "epoch": 0.68, + "learning_rate": 0.0007270408163265307, + "loss": 5.1008, "step": 609 }, { - "epoch": 0.34, - "learning_rate": 0.0009158878504672897, - "loss": 5.4971, + "epoch": 0.68, + "learning_rate": 0.0007244897959183674, + "loss": 5.1949, "step": 610 }, { - "epoch": 0.34, - "learning_rate": 0.0009151090342679128, - "loss": 6.5403, + "epoch": 0.68, + "learning_rate": 0.0007219387755102041, + "loss": 4.9015, "step": 611 }, { - "epoch": 0.34, - "learning_rate": 0.0009143302180685359, - "loss": 5.4691, + "epoch": 0.69, + "learning_rate": 0.0007193877551020408, + "loss": 5.1184, "step": 612 }, { - "epoch": 0.34, - "learning_rate": 0.0009135514018691589, - "loss": 5.6011, + "epoch": 0.69, + "learning_rate": 0.0007168367346938776, + "loss": 5.2819, "step": 613 }, { - "epoch": 0.34, - "learning_rate": 0.0009127725856697819, - "loss": 5.6706, + "epoch": 0.69, + "learning_rate": 0.0007142857142857143, + "loss": 5.0992, "step": 614 }, { - "epoch": 0.34, - "learning_rate": 0.000911993769470405, - "loss": 6.1429, + "epoch": 0.69, + "learning_rate": 0.0007117346938775511, + "loss": 5.1966, "step": 615 }, { - "epoch": 0.35, - "learning_rate": 0.0009112149532710281, - "loss": 5.5042, + "epoch": 0.69, + "learning_rate": 0.0007091836734693877, + "loss": 4.9135, "step": 616 }, { - "epoch": 0.35, - "learning_rate": 0.000910436137071651, - "loss": 6.0994, + "epoch": 0.69, + "learning_rate": 0.0007066326530612245, + "loss": 5.1225, "step": 617 }, { - "epoch": 0.35, - "learning_rate": 0.0009096573208722742, - "loss": 5.2208, + "epoch": 0.69, + "learning_rate": 0.0007040816326530613, + "loss": 4.8598, "step": 618 }, { - "epoch": 0.35, - "learning_rate": 0.0009088785046728972, - "loss": 5.5851, + "epoch": 0.69, + "learning_rate": 0.000701530612244898, + "loss": 4.8324, "step": 619 }, { - "epoch": 0.35, - "learning_rate": 0.0009080996884735203, - "loss": 5.9498, + "epoch": 0.7, + "learning_rate": 0.0006989795918367347, + "loss": 5.01, "step": 620 }, { - "epoch": 0.35, - "learning_rate": 0.0009073208722741433, - "loss": 5.6269, + "epoch": 0.7, + "learning_rate": 0.0006964285714285714, + "loss": 5.0319, "step": 621 }, { - "epoch": 0.35, - "learning_rate": 0.0009065420560747663, - "loss": 6.4999, + "epoch": 0.7, + "learning_rate": 0.0006938775510204082, + "loss": 4.9734, "step": 622 }, { - "epoch": 0.35, - "learning_rate": 0.0009057632398753895, - "loss": 5.548, + "epoch": 0.7, + "learning_rate": 0.0006913265306122449, + "loss": 5.05, "step": 623 }, { - "epoch": 0.35, - "learning_rate": 0.0009049844236760125, - "loss": 6.9756, + "epoch": 0.7, + "learning_rate": 0.0006887755102040817, + "loss": 5.0356, "step": 624 }, { - "epoch": 0.35, - "learning_rate": 0.0009042056074766354, - "loss": 6.6103, + "epoch": 0.7, + "learning_rate": 0.0006862244897959184, + "loss": 5.3868, "step": 625 }, { - "epoch": 0.35, - "learning_rate": 0.0009034267912772586, - "loss": 6.0082, + "epoch": 0.7, + "learning_rate": 0.0006836734693877551, + "loss": 5.0528, "step": 626 }, { - "epoch": 0.35, - "learning_rate": 0.0009026479750778816, - "loss": 5.6423, + "epoch": 0.7, + "learning_rate": 0.0006811224489795918, + "loss": 5.0486, "step": 627 }, { - "epoch": 0.35, - "learning_rate": 0.0009018691588785048, - "loss": 6.5811, + "epoch": 0.7, + "learning_rate": 0.0006785714285714287, + "loss": 4.9144, "step": 628 }, { - "epoch": 0.35, - "learning_rate": 0.0009010903426791277, - "loss": 7.2212, + "epoch": 0.71, + "learning_rate": 0.0006760204081632653, + "loss": 4.923, "step": 629 }, { - "epoch": 0.35, - "learning_rate": 0.0009003115264797507, - "loss": 5.5423, + "epoch": 0.71, + "learning_rate": 0.000673469387755102, + "loss": 5.2818, "step": 630 }, { - "epoch": 0.35, - "learning_rate": 0.0008995327102803739, - "loss": 5.7064, + "epoch": 0.71, + "learning_rate": 0.0006709183673469387, + "loss": 4.9389, "step": 631 }, { - "epoch": 0.35, - "learning_rate": 0.0008987538940809969, - "loss": 5.6349, + "epoch": 0.71, + "learning_rate": 0.0006683673469387756, + "loss": 5.6102, "step": 632 }, { - "epoch": 0.35, - "learning_rate": 0.00089797507788162, - "loss": 5.5361, + "epoch": 0.71, + "learning_rate": 0.0006658163265306123, + "loss": 5.0466, "step": 633 }, { - "epoch": 0.36, - "learning_rate": 0.000897196261682243, - "loss": 5.7571, + "epoch": 0.71, + "learning_rate": 0.0006632653061224489, + "loss": 4.9354, "step": 634 }, { - "epoch": 0.36, - "learning_rate": 0.000896417445482866, - "loss": 5.5642, + "epoch": 0.71, + "learning_rate": 0.0006607142857142857, + "loss": 5.1228, "step": 635 }, { - "epoch": 0.36, - "learning_rate": 0.0008956386292834892, - "loss": 5.6737, + "epoch": 0.71, + "learning_rate": 0.0006581632653061225, + "loss": 4.937, "step": 636 }, { - "epoch": 0.36, - "learning_rate": 0.0008948598130841121, - "loss": 5.4477, + "epoch": 0.71, + "learning_rate": 0.0006556122448979592, + "loss": 4.9867, "step": 637 }, { - "epoch": 0.36, - "learning_rate": 0.0008940809968847352, - "loss": 5.1446, + "epoch": 0.72, + "learning_rate": 0.0006530612244897959, + "loss": 4.7481, "step": 638 }, { - "epoch": 0.36, - "learning_rate": 0.0008933021806853583, - "loss": 5.7823, + "epoch": 0.72, + "learning_rate": 0.0006505102040816326, + "loss": 5.1057, "step": 639 }, { - "epoch": 0.36, - "learning_rate": 0.0008925233644859813, - "loss": 7.0817, + "epoch": 0.72, + "learning_rate": 0.0006479591836734694, + "loss": 4.8321, "step": 640 }, { - "epoch": 0.36, - "learning_rate": 0.0008917445482866044, - "loss": 6.5275, + "epoch": 0.72, + "learning_rate": 0.0006454081632653062, + "loss": 4.8926, "step": 641 }, { - "epoch": 0.36, - "learning_rate": 0.0008909657320872274, - "loss": 5.7894, + "epoch": 0.72, + "learning_rate": 0.0006428571428571429, + "loss": 6.7244, "step": 642 }, { - "epoch": 0.36, - "learning_rate": 0.0008901869158878505, - "loss": 6.6158, + "epoch": 0.72, + "learning_rate": 0.0006403061224489795, + "loss": 5.5171, "step": 643 }, { - "epoch": 0.36, - "learning_rate": 0.0008894080996884736, - "loss": 5.6095, + "epoch": 0.72, + "learning_rate": 0.0006377551020408163, + "loss": 4.8591, "step": 644 }, { - "epoch": 0.36, - "learning_rate": 0.0008886292834890965, - "loss": 5.1257, + "epoch": 0.72, + "learning_rate": 0.0006352040816326531, + "loss": 4.7389, "step": 645 }, { - "epoch": 0.36, - "learning_rate": 0.0008878504672897196, - "loss": 5.9652, + "epoch": 0.72, + "learning_rate": 0.0006326530612244898, + "loss": 4.997, "step": 646 }, { - "epoch": 0.36, - "learning_rate": 0.0008870716510903427, - "loss": 7.9338, + "epoch": 0.73, + "learning_rate": 0.0006301020408163265, + "loss": 4.9194, "step": 647 }, { - "epoch": 0.36, - "learning_rate": 0.0008862928348909658, - "loss": 8.5368, + "epoch": 0.73, + "learning_rate": 0.0006275510204081633, + "loss": 5.0819, "step": 648 }, { - "epoch": 0.36, - "learning_rate": 0.0008855140186915888, - "loss": 6.0364, + "epoch": 0.73, + "learning_rate": 0.000625, + "loss": 5.2145, "step": 649 }, { - "epoch": 0.36, - "learning_rate": 0.0008847352024922118, - "loss": 5.7585, + "epoch": 0.73, + "learning_rate": 0.0006224489795918367, + "loss": 4.8832, "step": 650 }, { - "epoch": 0.36, - "learning_rate": 0.0008839563862928349, - "loss": 6.2952, + "epoch": 0.73, + "learning_rate": 0.0006198979591836736, + "loss": 5.3171, "step": 651 }, { - "epoch": 0.37, - "learning_rate": 0.000883177570093458, - "loss": 5.4473, + "epoch": 0.73, + "learning_rate": 0.0006173469387755102, + "loss": 5.2764, "step": 652 }, { - "epoch": 0.37, - "learning_rate": 0.000882398753894081, - "loss": 5.5281, + "epoch": 0.73, + "learning_rate": 0.0006147959183673469, + "loss": 5.0498, "step": 653 }, { - "epoch": 0.37, - "learning_rate": 0.000881619937694704, - "loss": 5.5034, + "epoch": 0.73, + "learning_rate": 0.0006122448979591838, + "loss": 5.2789, "step": 654 }, { - "epoch": 0.37, - "learning_rate": 0.0008808411214953271, - "loss": 5.4803, + "epoch": 0.73, + "learning_rate": 0.0006096938775510205, + "loss": 4.9983, "step": 655 }, { - "epoch": 0.37, - "learning_rate": 0.0008800623052959502, - "loss": 5.3844, + "epoch": 0.74, + "learning_rate": 0.0006071428571428571, + "loss": 5.055, "step": 656 }, { - "epoch": 0.37, - "learning_rate": 0.0008792834890965732, - "loss": 5.3585, + "epoch": 0.74, + "learning_rate": 0.0006045918367346938, + "loss": 4.9124, "step": 657 }, { - "epoch": 0.37, - "learning_rate": 0.0008785046728971963, - "loss": 7.0488, + "epoch": 0.74, + "learning_rate": 0.0006020408163265307, + "loss": 5.1472, "step": 658 }, { - "epoch": 0.37, - "learning_rate": 0.0008777258566978193, - "loss": 5.7949, + "epoch": 0.74, + "learning_rate": 0.0005994897959183674, + "loss": 4.9621, "step": 659 }, { - "epoch": 0.37, - "learning_rate": 0.0008769470404984425, - "loss": 5.5483, + "epoch": 0.74, + "learning_rate": 0.0005969387755102041, + "loss": 5.1466, "step": 660 }, { - "epoch": 0.37, - "learning_rate": 0.0008761682242990654, - "loss": 6.0146, + "epoch": 0.74, + "learning_rate": 0.0005943877551020408, + "loss": 4.7999, "step": 661 }, { - "epoch": 0.37, - "learning_rate": 0.0008753894080996884, - "loss": 5.6606, + "epoch": 0.74, + "learning_rate": 0.0005918367346938776, + "loss": 4.7113, "step": 662 }, { - "epoch": 0.37, - "learning_rate": 0.0008746105919003116, - "loss": 5.5422, + "epoch": 0.74, + "learning_rate": 0.0005892857142857143, + "loss": 5.2727, "step": 663 }, { - "epoch": 0.37, - "learning_rate": 0.0008738317757009346, - "loss": 5.7667, + "epoch": 0.74, + "learning_rate": 0.0005867346938775511, + "loss": 4.9338, "step": 664 }, { - "epoch": 0.37, - "learning_rate": 0.0008730529595015576, - "loss": 5.3402, + "epoch": 0.75, + "learning_rate": 0.0005841836734693877, + "loss": 4.8416, "step": 665 }, { - "epoch": 0.37, - "learning_rate": 0.0008722741433021807, - "loss": 5.6747, + "epoch": 0.75, + "learning_rate": 0.0005816326530612245, + "loss": 5.1135, "step": 666 }, { - "epoch": 0.37, - "learning_rate": 0.0008714953271028037, - "loss": 5.6818, + "epoch": 0.75, + "learning_rate": 0.0005790816326530613, + "loss": 4.9375, "step": 667 }, { - "epoch": 0.37, - "learning_rate": 0.0008707165109034269, - "loss": 5.969, + "epoch": 0.75, + "learning_rate": 0.000576530612244898, + "loss": 4.909, "step": 668 }, { - "epoch": 0.38, - "learning_rate": 0.0008699376947040498, - "loss": 5.3574, + "epoch": 0.75, + "learning_rate": 0.0005739795918367347, + "loss": 5.1056, "step": 669 }, { - "epoch": 0.38, - "learning_rate": 0.000869158878504673, - "loss": 7.1095, + "epoch": 0.75, + "learning_rate": 0.0005714285714285714, + "loss": 5.0018, "step": 670 }, { - "epoch": 0.38, - "learning_rate": 0.000868380062305296, - "loss": 5.6812, + "epoch": 0.75, + "learning_rate": 0.0005688775510204082, + "loss": 4.7696, "step": 671 }, { - "epoch": 0.38, - "learning_rate": 0.000867601246105919, - "loss": 5.9285, + "epoch": 0.75, + "learning_rate": 0.0005663265306122449, + "loss": 4.9088, "step": 672 }, { - "epoch": 0.38, - "learning_rate": 0.0008668224299065421, - "loss": 5.357, + "epoch": 0.75, + "learning_rate": 0.0005637755102040816, + "loss": 4.7722, "step": 673 }, { - "epoch": 0.38, - "learning_rate": 0.0008660436137071651, - "loss": 5.2617, + "epoch": 0.76, + "learning_rate": 0.0005612244897959184, + "loss": 4.8107, "step": 674 }, { - "epoch": 0.38, - "learning_rate": 0.0008652647975077882, - "loss": 6.0633, + "epoch": 0.76, + "learning_rate": 0.0005586734693877551, + "loss": 4.9513, "step": 675 }, { - "epoch": 0.38, - "learning_rate": 0.0008644859813084113, - "loss": 5.481, + "epoch": 0.76, + "learning_rate": 0.0005561224489795918, + "loss": 5.549, "step": 676 }, { - "epoch": 0.38, - "learning_rate": 0.0008637071651090342, - "loss": 5.2393, + "epoch": 0.76, + "learning_rate": 0.0005535714285714287, + "loss": 4.8031, "step": 677 }, { - "epoch": 0.38, - "learning_rate": 0.0008629283489096574, - "loss": 5.413, + "epoch": 0.76, + "learning_rate": 0.0005510204081632653, + "loss": 4.6527, "step": 678 }, { - "epoch": 0.38, - "learning_rate": 0.0008621495327102804, - "loss": 5.9874, + "epoch": 0.76, + "learning_rate": 0.000548469387755102, + "loss": 4.8261, "step": 679 }, { - "epoch": 0.38, - "learning_rate": 0.0008613707165109035, - "loss": 5.6816, + "epoch": 0.76, + "learning_rate": 0.0005459183673469387, + "loss": 4.8573, "step": 680 }, { - "epoch": 0.38, - "learning_rate": 0.0008605919003115265, - "loss": 5.5351, + "epoch": 0.76, + "learning_rate": 0.0005433673469387756, + "loss": 5.1294, "step": 681 }, { - "epoch": 0.38, - "learning_rate": 0.0008598130841121495, - "loss": 5.3731, + "epoch": 0.76, + "learning_rate": 0.0005408163265306123, + "loss": 4.6851, "step": 682 }, { - "epoch": 0.38, - "learning_rate": 0.0008590342679127726, - "loss": 5.6922, + "epoch": 0.77, + "learning_rate": 0.0005382653061224489, + "loss": 5.119, "step": 683 }, { - "epoch": 0.38, - "learning_rate": 0.0008582554517133957, - "loss": 5.6893, + "epoch": 0.77, + "learning_rate": 0.0005357142857142857, + "loss": 5.217, "step": 684 }, { - "epoch": 0.38, - "learning_rate": 0.0008574766355140187, - "loss": 5.6571, + "epoch": 0.77, + "learning_rate": 0.0005331632653061225, + "loss": 4.9345, "step": 685 }, { - "epoch": 0.38, - "learning_rate": 0.0008566978193146418, - "loss": 5.7211, + "epoch": 0.77, + "learning_rate": 0.0005306122448979592, + "loss": 5.0111, "step": 686 }, { - "epoch": 0.39, - "learning_rate": 0.0008559190031152648, - "loss": 6.3004, + "epoch": 0.77, + "learning_rate": 0.0005280612244897959, + "loss": 4.9354, "step": 687 }, { - "epoch": 0.39, - "learning_rate": 0.0008551401869158879, - "loss": 5.4837, + "epoch": 0.77, + "learning_rate": 0.0005255102040816326, + "loss": 4.9864, "step": 688 }, { - "epoch": 0.39, - "learning_rate": 0.0008543613707165109, - "loss": 6.2322, + "epoch": 0.77, + "learning_rate": 0.0005229591836734694, + "loss": 4.9079, "step": 689 }, { - "epoch": 0.39, - "learning_rate": 0.000853582554517134, - "loss": 5.4185, + "epoch": 0.77, + "learning_rate": 0.0005204081632653062, + "loss": 5.2492, "step": 690 }, { - "epoch": 0.39, - "learning_rate": 0.000852803738317757, - "loss": 5.3541, + "epoch": 0.77, + "learning_rate": 0.0005178571428571429, + "loss": 4.9012, "step": 691 }, { - "epoch": 0.39, - "learning_rate": 0.0008520249221183801, - "loss": 5.7813, + "epoch": 0.78, + "learning_rate": 0.0005153061224489795, + "loss": 4.9484, "step": 692 }, { - "epoch": 0.39, - "learning_rate": 0.0008512461059190031, - "loss": 5.7453, + "epoch": 0.78, + "learning_rate": 0.0005127551020408163, + "loss": 4.7525, "step": 693 }, { - "epoch": 0.39, - "learning_rate": 0.0008504672897196262, - "loss": 5.5721, + "epoch": 0.78, + "learning_rate": 0.0005102040816326531, + "loss": 5.2413, "step": 694 }, { - "epoch": 0.39, - "learning_rate": 0.0008496884735202493, - "loss": 5.4339, + "epoch": 0.78, + "learning_rate": 0.0005076530612244898, + "loss": 5.0768, "step": 695 }, { - "epoch": 0.39, - "learning_rate": 0.0008489096573208723, - "loss": 5.3716, + "epoch": 0.78, + "learning_rate": 0.0005051020408163265, + "loss": 5.1833, "step": 696 }, { - "epoch": 0.39, - "learning_rate": 0.0008481308411214953, - "loss": 5.194, + "epoch": 0.78, + "learning_rate": 0.0005025510204081633, + "loss": 5.3869, "step": 697 }, { - "epoch": 0.39, - "learning_rate": 0.0008473520249221184, - "loss": 5.3447, + "epoch": 0.78, + "learning_rate": 0.0005, + "loss": 5.0354, "step": 698 }, { - "epoch": 0.39, - "learning_rate": 0.0008465732087227414, - "loss": 5.7316, + "epoch": 0.78, + "learning_rate": 0.0004974489795918367, + "loss": 5.0789, "step": 699 }, { - "epoch": 0.39, - "learning_rate": 0.0008457943925233646, - "loss": 5.5159, + "epoch": 0.78, + "learning_rate": 0.0004948979591836735, + "loss": 4.9279, "step": 700 }, { - "epoch": 0.39, - "learning_rate": 0.0008450155763239875, - "loss": 5.3401, + "epoch": 0.79, + "learning_rate": 0.0004923469387755102, + "loss": 4.7946, "step": 701 }, { - "epoch": 0.39, - "learning_rate": 0.0008442367601246106, - "loss": 5.43, + "epoch": 0.79, + "learning_rate": 0.0004897959183673469, + "loss": 4.9595, "step": 702 }, { - "epoch": 0.39, - "learning_rate": 0.0008434579439252337, - "loss": 6.3139, + "epoch": 0.79, + "learning_rate": 0.0004872448979591837, + "loss": 4.7994, "step": 703 }, { - "epoch": 0.39, - "learning_rate": 0.0008426791277258567, - "loss": 6.924, + "epoch": 0.79, + "learning_rate": 0.0004846938775510204, + "loss": 4.9163, "step": 704 }, { - "epoch": 0.4, - "learning_rate": 0.0008419003115264798, - "loss": 7.0024, + "epoch": 0.79, + "learning_rate": 0.00048214285714285715, + "loss": 4.9548, "step": 705 }, { - "epoch": 0.4, - "learning_rate": 0.0008411214953271028, - "loss": 5.9137, + "epoch": 0.79, + "learning_rate": 0.00047959183673469387, + "loss": 5.1581, "step": 706 }, { - "epoch": 0.4, - "learning_rate": 0.0008403426791277258, - "loss": 6.0214, + "epoch": 0.79, + "learning_rate": 0.00047704081632653065, + "loss": 4.9996, "step": 707 }, { - "epoch": 0.4, - "learning_rate": 0.000839563862928349, - "loss": 5.769, + "epoch": 0.79, + "learning_rate": 0.0004744897959183674, + "loss": 5.1511, "step": 708 }, { - "epoch": 0.4, - "learning_rate": 0.0008387850467289719, - "loss": 6.0759, + "epoch": 0.79, + "learning_rate": 0.0004719387755102041, + "loss": 4.9985, "step": 709 }, { - "epoch": 0.4, - "learning_rate": 0.0008380062305295951, - "loss": 5.803, + "epoch": 0.8, + "learning_rate": 0.00046938775510204083, + "loss": 5.0571, "step": 710 }, { - "epoch": 0.4, - "learning_rate": 0.0008372274143302181, - "loss": 6.0019, + "epoch": 0.8, + "learning_rate": 0.00046683673469387755, + "loss": 5.1134, "step": 711 }, { - "epoch": 0.4, - "learning_rate": 0.0008364485981308411, - "loss": 5.7339, + "epoch": 0.8, + "learning_rate": 0.00046428571428571433, + "loss": 4.7978, "step": 712 }, { - "epoch": 0.4, - "learning_rate": 0.0008356697819314642, - "loss": 5.9036, + "epoch": 0.8, + "learning_rate": 0.000461734693877551, + "loss": 4.6712, "step": 713 }, { - "epoch": 0.4, - "learning_rate": 0.0008348909657320872, - "loss": 6.09, + "epoch": 0.8, + "learning_rate": 0.0004591836734693878, + "loss": 4.9959, "step": 714 }, { - "epoch": 0.4, - "learning_rate": 0.0008341121495327104, - "loss": 6.4507, + "epoch": 0.8, + "learning_rate": 0.00045663265306122446, + "loss": 5.1947, "step": 715 }, { - "epoch": 0.4, - "learning_rate": 0.0008333333333333334, - "loss": 6.0299, + "epoch": 0.8, + "learning_rate": 0.00045408163265306124, + "loss": 4.8231, "step": 716 }, { - "epoch": 0.4, - "learning_rate": 0.0008325545171339563, - "loss": 5.5245, + "epoch": 0.8, + "learning_rate": 0.00045153061224489796, + "loss": 5.09, "step": 717 }, { - "epoch": 0.4, - "learning_rate": 0.0008317757009345795, - "loss": 7.4586, + "epoch": 0.8, + "learning_rate": 0.0004489795918367347, + "loss": 4.7469, "step": 718 }, { - "epoch": 0.4, - "learning_rate": 0.0008317757009345795, - "loss": 127.5589, + "epoch": 0.81, + "learning_rate": 0.00044642857142857147, + "loss": 4.8668, "step": 719 }, { - "epoch": 0.4, - "learning_rate": 0.0008317757009345795, - "loss": 127.6926, + "epoch": 0.81, + "learning_rate": 0.00044387755102040814, + "loss": 4.841, "step": 720 }, { - "epoch": 0.4, - "learning_rate": 0.0008309968847352025, - "loss": 128.0117, + "epoch": 0.81, + "learning_rate": 0.0004413265306122449, + "loss": 4.7433, "step": 721 }, { - "epoch": 0.4, - "learning_rate": 0.0008302180685358256, - "loss": 7.304, + "epoch": 0.81, + "learning_rate": 0.00043877551020408165, + "loss": 4.7101, "step": 722 }, { - "epoch": 0.41, - "learning_rate": 0.0008294392523364486, - "loss": 34.3362, + "epoch": 0.81, + "learning_rate": 0.00043622448979591837, + "loss": 4.8642, "step": 723 }, { - "epoch": 0.41, - "learning_rate": 0.0008286604361370716, - "loss": 8.2908, + "epoch": 0.81, + "learning_rate": 0.0004336734693877551, + "loss": 4.9878, "step": 724 }, { - "epoch": 0.41, - "learning_rate": 0.0008286604361370716, - "loss": 353.4574, + "epoch": 0.81, + "learning_rate": 0.0004311224489795919, + "loss": 4.8054, "step": 725 }, { - "epoch": 0.41, - "learning_rate": 0.0008286604361370716, - "loss": 362.119, + "epoch": 0.81, + "learning_rate": 0.00042857142857142855, + "loss": 5.0236, "step": 726 }, { - "epoch": 0.41, - "learning_rate": 0.0008278816199376947, - "loss": 364.2142, + "epoch": 0.82, + "learning_rate": 0.00042602040816326533, + "loss": 4.8533, "step": 727 }, { - "epoch": 0.41, - "learning_rate": 0.0008271028037383178, - "loss": 7.9371, + "epoch": 0.82, + "learning_rate": 0.00042346938775510206, + "loss": 4.6959, "step": 728 }, { - "epoch": 0.41, - "learning_rate": 0.0008263239875389408, - "loss": 6.7483, + "epoch": 0.82, + "learning_rate": 0.0004209183673469388, + "loss": 4.6739, "step": 729 }, { - "epoch": 0.41, - "learning_rate": 0.0008255451713395639, - "loss": 5.8504, + "epoch": 0.82, + "learning_rate": 0.00041836734693877556, + "loss": 5.0312, "step": 730 }, { - "epoch": 0.41, - "learning_rate": 0.0008247663551401869, - "loss": 5.7046, + "epoch": 0.82, + "learning_rate": 0.00041581632653061223, + "loss": 5.2839, "step": 731 }, { - "epoch": 0.41, - "learning_rate": 0.00082398753894081, - "loss": 5.5892, + "epoch": 0.82, + "learning_rate": 0.000413265306122449, + "loss": 4.9503, "step": 732 }, { - "epoch": 0.41, - "learning_rate": 0.000823208722741433, - "loss": 7.1147, + "epoch": 0.82, + "learning_rate": 0.0004107142857142857, + "loss": 4.8103, "step": 733 }, { - "epoch": 0.41, - "learning_rate": 0.0008224299065420561, - "loss": 5.7482, + "epoch": 0.82, + "learning_rate": 0.00040816326530612246, + "loss": 4.9057, "step": 734 }, { - "epoch": 0.41, - "learning_rate": 0.0008216510903426791, - "loss": 7.1636, + "epoch": 0.82, + "learning_rate": 0.0004056122448979592, + "loss": 4.6994, "step": 735 }, { - "epoch": 0.41, - "learning_rate": 0.0008208722741433022, - "loss": 5.5311, + "epoch": 0.83, + "learning_rate": 0.0004030612244897959, + "loss": 4.8075, "step": 736 }, { - "epoch": 0.41, - "learning_rate": 0.0008200934579439252, - "loss": 8.5084, + "epoch": 0.83, + "learning_rate": 0.00040051020408163264, + "loss": 4.8765, "step": 737 }, { - "epoch": 0.41, - "learning_rate": 0.0008193146417445483, - "loss": 8.1499, + "epoch": 0.83, + "learning_rate": 0.00039795918367346937, + "loss": 4.843, "step": 738 }, { - "epoch": 0.41, - "learning_rate": 0.0008185358255451714, - "loss": 8.2757, + "epoch": 0.83, + "learning_rate": 0.00039540816326530615, + "loss": 4.6777, "step": 739 }, { - "epoch": 0.41, - "learning_rate": 0.0008177570093457944, - "loss": 7.8709, + "epoch": 0.83, + "learning_rate": 0.0003928571428571429, + "loss": 5.0097, "step": 740 }, { - "epoch": 0.42, - "learning_rate": 0.0008169781931464174, - "loss": 19.0706, + "epoch": 0.83, + "learning_rate": 0.0003903061224489796, + "loss": 5.0502, "step": 741 }, { - "epoch": 0.42, - "learning_rate": 0.0008161993769470405, - "loss": 7.6099, + "epoch": 0.83, + "learning_rate": 0.0003877551020408163, + "loss": 4.7957, "step": 742 }, { - "epoch": 0.42, - "learning_rate": 0.0008154205607476635, - "loss": 9.2035, + "epoch": 0.83, + "learning_rate": 0.0003852040816326531, + "loss": 4.6631, "step": 743 }, { - "epoch": 0.42, - "learning_rate": 0.0008154205607476635, - "loss": 60.3691, + "epoch": 0.83, + "learning_rate": 0.0003826530612244898, + "loss": 4.8876, "step": 744 }, { - "epoch": 0.42, - "learning_rate": 0.0008154205607476635, - "loss": 62.6483, + "epoch": 0.84, + "learning_rate": 0.00038010204081632656, + "loss": 4.6636, "step": 745 }, { - "epoch": 0.42, - "learning_rate": 0.0008154205607476635, - "loss": 65.7865, + "epoch": 0.84, + "learning_rate": 0.00037755102040816323, + "loss": 5.2342, "step": 746 }, { - "epoch": 0.42, - "learning_rate": 0.0008146417445482867, - "loss": 68.4556, + "epoch": 0.84, + "learning_rate": 0.000375, + "loss": 4.753, "step": 747 }, { - "epoch": 0.42, - "learning_rate": 0.0008138629283489096, - "loss": 12.1777, + "epoch": 0.84, + "learning_rate": 0.0003724489795918368, + "loss": 4.8729, "step": 748 }, { - "epoch": 0.42, - "learning_rate": 0.0008130841121495327, - "loss": 8.0897, + "epoch": 0.84, + "learning_rate": 0.00036989795918367346, + "loss": 5.0168, "step": 749 }, { - "epoch": 0.42, - "learning_rate": 0.0008123052959501558, - "loss": 7.5521, + "epoch": 0.84, + "learning_rate": 0.00036734693877551024, + "loss": 4.9339, "step": 750 }, { - "epoch": 0.42, - "learning_rate": 0.0008115264797507788, - "loss": 8.4163, + "epoch": 0.84, + "learning_rate": 0.0003647959183673469, + "loss": 4.9065, "step": 751 }, { - "epoch": 0.42, - "learning_rate": 0.0008115264797507788, - "loss": 367.311, + "epoch": 0.84, + "learning_rate": 0.0003622448979591837, + "loss": 4.8276, "step": 752 }, { - "epoch": 0.42, - "learning_rate": 0.0008107476635514019, - "loss": 352.5347, + "epoch": 0.84, + "learning_rate": 0.0003596938775510204, + "loss": 4.8596, "step": 753 }, { - "epoch": 0.42, - "learning_rate": 0.0008099688473520249, - "loss": 230.6191, + "epoch": 0.85, + "learning_rate": 0.00035714285714285714, + "loss": 4.8511, "step": 754 }, { - "epoch": 0.42, - "learning_rate": 0.000809190031152648, - "loss": 7.8892, + "epoch": 0.85, + "learning_rate": 0.00035459183673469387, + "loss": 4.8633, "step": 755 }, { - "epoch": 0.42, - "learning_rate": 0.0008084112149532711, - "loss": 8.3983, + "epoch": 0.85, + "learning_rate": 0.00035204081632653065, + "loss": 5.1471, "step": 756 }, { - "epoch": 0.42, - "learning_rate": 0.000807632398753894, - "loss": 7.69, + "epoch": 0.85, + "learning_rate": 0.0003494897959183674, + "loss": 5.0629, "step": 757 }, { - "epoch": 0.42, - "learning_rate": 0.0008068535825545172, - "loss": 7.6752, + "epoch": 0.85, + "learning_rate": 0.0003469387755102041, + "loss": 4.8626, "step": 758 }, { - "epoch": 0.43, - "learning_rate": 0.0008060747663551402, - "loss": 7.5937, + "epoch": 0.85, + "learning_rate": 0.0003443877551020408, + "loss": 4.7699, "step": 759 }, { - "epoch": 0.43, - "learning_rate": 0.0008052959501557632, - "loss": 7.2027, + "epoch": 0.85, + "learning_rate": 0.00034183673469387755, + "loss": 4.7787, "step": 760 }, { - "epoch": 0.43, - "learning_rate": 0.0008045171339563863, - "loss": 96.2049, + "epoch": 0.85, + "learning_rate": 0.00033928571428571433, + "loss": 4.8297, "step": 761 }, { - "epoch": 0.43, - "learning_rate": 0.0008037383177570093, - "loss": 9.6606, + "epoch": 0.85, + "learning_rate": 0.000336734693877551, + "loss": 4.6865, "step": 762 }, { - "epoch": 0.43, - "learning_rate": 0.0008029595015576325, - "loss": 8.2116, + "epoch": 0.86, + "learning_rate": 0.0003341836734693878, + "loss": 4.691, "step": 763 }, { - "epoch": 0.43, - "learning_rate": 0.0008021806853582555, - "loss": 7.5096, + "epoch": 0.86, + "learning_rate": 0.00033163265306122445, + "loss": 4.5826, "step": 764 }, { - "epoch": 0.43, - "learning_rate": 0.0008014018691588784, - "loss": 7.2209, + "epoch": 0.86, + "learning_rate": 0.00032908163265306123, + "loss": 5.1117, "step": 765 }, { - "epoch": 0.43, - "learning_rate": 0.0008006230529595016, - "loss": 7.2376, + "epoch": 0.86, + "learning_rate": 0.00032653061224489796, + "loss": 5.0025, "step": 766 }, { - "epoch": 0.43, - "learning_rate": 0.0007998442367601246, - "loss": 7.4804, + "epoch": 0.86, + "learning_rate": 0.0003239795918367347, + "loss": 4.6712, "step": 767 }, { - "epoch": 0.43, - "learning_rate": 0.0007990654205607477, - "loss": 7.8516, + "epoch": 0.86, + "learning_rate": 0.00032142857142857147, + "loss": 5.162, "step": 768 }, { - "epoch": 0.43, - "learning_rate": 0.0007982866043613707, - "loss": 7.4039, + "epoch": 0.86, + "learning_rate": 0.00031887755102040814, + "loss": 4.8693, "step": 769 }, { - "epoch": 0.43, - "learning_rate": 0.0007975077881619937, - "loss": 7.2151, + "epoch": 0.86, + "learning_rate": 0.0003163265306122449, + "loss": 4.7581, "step": 770 }, { - "epoch": 0.43, - "learning_rate": 0.0007967289719626169, - "loss": 7.9842, + "epoch": 0.86, + "learning_rate": 0.00031377551020408164, + "loss": 4.7253, "step": 771 }, { - "epoch": 0.43, - "learning_rate": 0.0007959501557632399, - "loss": 7.3203, + "epoch": 0.87, + "learning_rate": 0.00031122448979591837, + "loss": 4.8999, "step": 772 }, { - "epoch": 0.43, - "learning_rate": 0.0007951713395638629, - "loss": 7.1059, + "epoch": 0.87, + "learning_rate": 0.0003086734693877551, + "loss": 4.9918, "step": 773 }, { - "epoch": 0.43, - "learning_rate": 0.000794392523364486, - "loss": 7.7233, + "epoch": 0.87, + "learning_rate": 0.0003061224489795919, + "loss": 4.5347, "step": 774 }, { - "epoch": 0.43, - "learning_rate": 0.000793613707165109, - "loss": 6.9973, + "epoch": 0.87, + "learning_rate": 0.00030357142857142855, + "loss": 4.4954, "step": 775 }, { - "epoch": 0.43, - "learning_rate": 0.0007928348909657321, - "loss": 7.3334, + "epoch": 0.87, + "learning_rate": 0.0003010204081632653, + "loss": 5.0078, "step": 776 }, { - "epoch": 0.44, - "learning_rate": 0.0007920560747663551, - "loss": 7.405, + "epoch": 0.87, + "learning_rate": 0.00029846938775510205, + "loss": 4.6184, "step": 777 }, { - "epoch": 0.44, - "learning_rate": 0.0007912772585669782, - "loss": 6.9574, + "epoch": 0.87, + "learning_rate": 0.0002959183673469388, + "loss": 4.9227, "step": 778 }, { - "epoch": 0.44, - "learning_rate": 0.0007904984423676013, - "loss": 7.3522, + "epoch": 0.87, + "learning_rate": 0.00029336734693877556, + "loss": 4.667, "step": 779 }, { - "epoch": 0.44, - "learning_rate": 0.0007897196261682244, - "loss": 7.1215, + "epoch": 0.87, + "learning_rate": 0.00029081632653061223, + "loss": 4.7333, "step": 780 }, { - "epoch": 0.44, - "learning_rate": 0.0007889408099688473, - "loss": 6.7281, + "epoch": 0.88, + "learning_rate": 0.000288265306122449, + "loss": 4.6473, "step": 781 }, { - "epoch": 0.44, - "learning_rate": 0.0007881619937694704, - "loss": 6.6109, + "epoch": 0.88, + "learning_rate": 0.0002857142857142857, + "loss": 4.7418, "step": 782 }, { - "epoch": 0.44, - "learning_rate": 0.0007873831775700935, - "loss": 6.7925, + "epoch": 0.88, + "learning_rate": 0.00028316326530612246, + "loss": 4.8777, "step": 783 }, { - "epoch": 0.44, - "learning_rate": 0.0007866043613707165, - "loss": 6.2217, + "epoch": 0.88, + "learning_rate": 0.0002806122448979592, + "loss": 4.5377, "step": 784 }, { - "epoch": 0.44, - "learning_rate": 0.0007858255451713396, - "loss": 5.9927, + "epoch": 0.88, + "learning_rate": 0.0002780612244897959, + "loss": 4.7229, "step": 785 }, { - "epoch": 0.44, - "learning_rate": 0.0007850467289719626, - "loss": 6.5712, + "epoch": 0.88, + "learning_rate": 0.00027551020408163264, + "loss": 4.6596, "step": 786 }, { - "epoch": 0.44, - "learning_rate": 0.0007842679127725857, - "loss": 6.2222, + "epoch": 0.88, + "learning_rate": 0.00027295918367346936, + "loss": 4.8652, "step": 787 }, { - "epoch": 0.44, - "learning_rate": 0.0007834890965732088, - "loss": 6.3317, + "epoch": 0.88, + "learning_rate": 0.00027040816326530614, + "loss": 4.8039, "step": 788 }, { - "epoch": 0.44, - "learning_rate": 0.0007827102803738317, - "loss": 5.8298, + "epoch": 0.88, + "learning_rate": 0.00026785714285714287, + "loss": 4.7242, "step": 789 }, { - "epoch": 0.44, - "learning_rate": 0.0007819314641744549, - "loss": 6.2519, + "epoch": 0.89, + "learning_rate": 0.0002653061224489796, + "loss": 4.7512, "step": 790 }, { - "epoch": 0.44, - "learning_rate": 0.0007811526479750779, - "loss": 5.9925, + "epoch": 0.89, + "learning_rate": 0.0002627551020408163, + "loss": 4.75, "step": 791 }, { - "epoch": 0.44, - "learning_rate": 0.0007803738317757009, - "loss": 5.6268, + "epoch": 0.89, + "learning_rate": 0.0002602040816326531, + "loss": 4.5709, "step": 792 }, { - "epoch": 0.44, - "learning_rate": 0.000779595015576324, - "loss": 5.8292, + "epoch": 0.89, + "learning_rate": 0.0002576530612244898, + "loss": 4.7332, "step": 793 }, { - "epoch": 0.45, - "learning_rate": 0.000778816199376947, - "loss": 5.703, + "epoch": 0.89, + "learning_rate": 0.00025510204081632655, + "loss": 4.8817, "step": 794 }, { - "epoch": 0.45, - "learning_rate": 0.0007780373831775702, - "loss": 5.8214, + "epoch": 0.89, + "learning_rate": 0.0002525510204081632, + "loss": 4.9428, "step": 795 }, { - "epoch": 0.45, - "learning_rate": 0.0007772585669781932, - "loss": 6.0823, + "epoch": 0.89, + "learning_rate": 0.00025, + "loss": 4.5729, "step": 796 }, { - "epoch": 0.45, - "learning_rate": 0.0007764797507788161, - "loss": 6.0278, + "epoch": 0.89, + "learning_rate": 0.00024744897959183673, + "loss": 4.8771, "step": 797 }, { - "epoch": 0.45, - "learning_rate": 0.0007757009345794393, - "loss": 6.0999, + "epoch": 0.89, + "learning_rate": 0.00024489795918367346, + "loss": 4.8702, "step": 798 }, { - "epoch": 0.45, - "learning_rate": 0.0007749221183800623, - "loss": 6.0653, + "epoch": 0.9, + "learning_rate": 0.0002423469387755102, + "loss": 5.4777, "step": 799 }, { - "epoch": 0.45, - "learning_rate": 0.0007741433021806855, - "loss": 5.8895, + "epoch": 0.9, + "learning_rate": 0.00023979591836734694, + "loss": 5.01, "step": 800 }, { - "epoch": 0.45, - "learning_rate": 0.0007733644859813084, - "loss": 5.8237, + "epoch": 0.9, + "learning_rate": 0.0002372448979591837, + "loss": 4.8871, "step": 801 }, { - "epoch": 0.45, - "learning_rate": 0.0007725856697819314, - "loss": 5.7893, + "epoch": 0.9, + "learning_rate": 0.00023469387755102041, + "loss": 4.6433, "step": 802 }, { - "epoch": 0.45, - "learning_rate": 0.0007718068535825546, - "loss": 6.3667, + "epoch": 0.9, + "learning_rate": 0.00023214285714285717, + "loss": 4.8369, "step": 803 }, { - "epoch": 0.45, - "learning_rate": 0.0007710280373831776, - "loss": 5.6187, + "epoch": 0.9, + "learning_rate": 0.0002295918367346939, + "loss": 4.7214, "step": 804 }, { - "epoch": 0.45, - "learning_rate": 0.0007702492211838006, - "loss": 6.1788, + "epoch": 0.9, + "learning_rate": 0.00022704081632653062, + "loss": 4.5577, "step": 805 }, { - "epoch": 0.45, - "learning_rate": 0.0007694704049844237, - "loss": 5.9224, + "epoch": 0.9, + "learning_rate": 0.00022448979591836734, + "loss": 4.9597, "step": 806 }, { - "epoch": 0.45, - "learning_rate": 0.0007686915887850467, - "loss": 5.7043, + "epoch": 0.9, + "learning_rate": 0.00022193877551020407, + "loss": 4.6841, "step": 807 }, { - "epoch": 0.45, - "learning_rate": 0.0007679127725856699, - "loss": 5.3459, + "epoch": 0.91, + "learning_rate": 0.00021938775510204082, + "loss": 4.6865, "step": 808 }, { - "epoch": 0.45, - "learning_rate": 0.0007671339563862928, - "loss": 5.6664, + "epoch": 0.91, + "learning_rate": 0.00021683673469387755, + "loss": 4.9089, "step": 809 }, { - "epoch": 0.45, - "learning_rate": 0.0007663551401869159, - "loss": 5.8922, + "epoch": 0.91, + "learning_rate": 0.00021428571428571427, + "loss": 4.4829, "step": 810 }, { - "epoch": 0.45, - "learning_rate": 0.000765576323987539, - "loss": 5.4932, + "epoch": 0.91, + "learning_rate": 0.00021173469387755103, + "loss": 4.8973, "step": 811 }, { - "epoch": 0.46, - "learning_rate": 0.000764797507788162, - "loss": 5.7549, + "epoch": 0.91, + "learning_rate": 0.00020918367346938778, + "loss": 4.8187, "step": 812 }, { - "epoch": 0.46, - "learning_rate": 0.000764018691588785, - "loss": 5.8057, + "epoch": 0.91, + "learning_rate": 0.0002066326530612245, + "loss": 4.5545, "step": 813 }, { - "epoch": 0.46, - "learning_rate": 0.0007632398753894081, - "loss": 5.3238, + "epoch": 0.91, + "learning_rate": 0.00020408163265306123, + "loss": 4.7104, "step": 814 }, { - "epoch": 0.46, - "learning_rate": 0.0007624610591900312, - "loss": 5.6348, + "epoch": 0.91, + "learning_rate": 0.00020153061224489796, + "loss": 4.5445, "step": 815 }, { - "epoch": 0.46, - "learning_rate": 0.0007616822429906543, - "loss": 5.4811, + "epoch": 0.91, + "learning_rate": 0.00019897959183673468, + "loss": 4.6521, "step": 816 }, { - "epoch": 0.46, - "learning_rate": 0.0007609034267912772, - "loss": 5.8736, + "epoch": 0.92, + "learning_rate": 0.00019642857142857144, + "loss": 4.762, "step": 817 }, { - "epoch": 0.46, - "learning_rate": 0.0007601246105919003, - "loss": 5.684, + "epoch": 0.92, + "learning_rate": 0.00019387755102040816, + "loss": 4.6711, "step": 818 }, { - "epoch": 0.46, - "learning_rate": 0.0007593457943925234, - "loss": 5.5351, + "epoch": 0.92, + "learning_rate": 0.0001913265306122449, + "loss": 4.7525, "step": 819 }, { - "epoch": 0.46, - "learning_rate": 0.0007585669781931465, - "loss": 5.5375, + "epoch": 0.92, + "learning_rate": 0.00018877551020408161, + "loss": 4.6909, "step": 820 }, { - "epoch": 0.46, - "learning_rate": 0.0007577881619937694, - "loss": 5.5663, + "epoch": 0.92, + "learning_rate": 0.0001862244897959184, + "loss": 4.628, "step": 821 }, { - "epoch": 0.46, - "learning_rate": 0.0007570093457943925, - "loss": 28.2445, + "epoch": 0.92, + "learning_rate": 0.00018367346938775512, + "loss": 4.4963, "step": 822 }, { - "epoch": 0.46, - "learning_rate": 0.0007562305295950156, - "loss": 6.9171, + "epoch": 0.92, + "learning_rate": 0.00018112244897959185, + "loss": 4.6785, "step": 823 }, { - "epoch": 0.46, - "learning_rate": 0.0007554517133956387, - "loss": 5.7559, + "epoch": 0.92, + "learning_rate": 0.00017857142857142857, + "loss": 4.6588, "step": 824 }, { - "epoch": 0.46, - "learning_rate": 0.0007546728971962617, - "loss": 5.7685, + "epoch": 0.92, + "learning_rate": 0.00017602040816326532, + "loss": 5.0121, "step": 825 }, { - "epoch": 0.46, - "learning_rate": 0.0007538940809968847, - "loss": 5.5401, + "epoch": 0.93, + "learning_rate": 0.00017346938775510205, + "loss": 4.7394, "step": 826 }, { - "epoch": 0.46, - "learning_rate": 0.0007531152647975078, - "loss": 5.8127, + "epoch": 0.93, + "learning_rate": 0.00017091836734693878, + "loss": 4.6542, "step": 827 }, { - "epoch": 0.46, - "learning_rate": 0.0007523364485981309, - "loss": 5.6924, + "epoch": 0.93, + "learning_rate": 0.0001683673469387755, + "loss": 4.5092, "step": 828 }, { - "epoch": 0.46, - "learning_rate": 0.0007515576323987538, - "loss": 5.7264, + "epoch": 0.93, + "learning_rate": 0.00016581632653061223, + "loss": 4.5507, "step": 829 }, { - "epoch": 0.47, - "learning_rate": 0.000750778816199377, - "loss": 5.5022, + "epoch": 0.93, + "learning_rate": 0.00016326530612244898, + "loss": 4.8904, "step": 830 }, { - "epoch": 0.47, - "learning_rate": 0.00075, - "loss": 5.8572, + "epoch": 0.93, + "learning_rate": 0.00016071428571428573, + "loss": 4.4503, "step": 831 }, { - "epoch": 0.47, - "learning_rate": 0.000749221183800623, - "loss": 6.1063, + "epoch": 0.93, + "learning_rate": 0.00015816326530612246, + "loss": 4.5233, "step": 832 }, { - "epoch": 0.47, - "learning_rate": 0.0007484423676012462, - "loss": 5.6782, + "epoch": 0.93, + "learning_rate": 0.00015561224489795918, + "loss": 4.7851, "step": 833 }, { - "epoch": 0.47, - "learning_rate": 0.0007476635514018691, - "loss": 5.1067, + "epoch": 0.93, + "learning_rate": 0.00015306122448979594, + "loss": 4.5912, "step": 834 }, { - "epoch": 0.47, - "learning_rate": 0.0007468847352024923, - "loss": 5.3408, + "epoch": 0.94, + "learning_rate": 0.00015051020408163266, + "loss": 4.5898, "step": 835 }, { - "epoch": 0.47, - "learning_rate": 0.0007461059190031153, - "loss": 5.5264, + "epoch": 0.94, + "learning_rate": 0.0001479591836734694, + "loss": 4.782, "step": 836 }, { - "epoch": 0.47, - "learning_rate": 0.0007453271028037383, - "loss": 5.5262, + "epoch": 0.94, + "learning_rate": 0.00014540816326530611, + "loss": 4.5167, "step": 837 }, { - "epoch": 0.47, - "learning_rate": 0.0007445482866043614, - "loss": 5.2737, + "epoch": 0.94, + "learning_rate": 0.00014285714285714284, + "loss": 4.8074, "step": 838 }, { - "epoch": 0.47, - "learning_rate": 0.0007437694704049844, - "loss": 5.6015, + "epoch": 0.94, + "learning_rate": 0.0001403061224489796, + "loss": 4.5436, "step": 839 }, { - "epoch": 0.47, - "learning_rate": 0.0007429906542056076, - "loss": 5.8701, + "epoch": 0.94, + "learning_rate": 0.00013775510204081632, + "loss": 4.7421, "step": 840 }, { - "epoch": 0.47, - "learning_rate": 0.0007422118380062306, - "loss": 7.6387, + "epoch": 0.94, + "learning_rate": 0.00013520408163265307, + "loss": 4.833, "step": 841 }, { - "epoch": 0.47, - "learning_rate": 0.0007414330218068535, - "loss": 5.3155, + "epoch": 0.94, + "learning_rate": 0.0001326530612244898, + "loss": 4.5748, "step": 842 }, { - "epoch": 0.47, - "learning_rate": 0.0007406542056074767, - "loss": 5.4614, + "epoch": 0.95, + "learning_rate": 0.00013010204081632655, + "loss": 4.9057, "step": 843 }, { - "epoch": 0.47, - "learning_rate": 0.0007398753894080997, - "loss": 5.722, + "epoch": 0.95, + "learning_rate": 0.00012755102040816328, + "loss": 4.7376, "step": 844 }, { - "epoch": 0.47, - "learning_rate": 0.0007390965732087229, - "loss": 5.1268, + "epoch": 0.95, + "learning_rate": 0.000125, + "loss": 4.9631, "step": 845 }, { - "epoch": 0.47, - "learning_rate": 0.0007383177570093458, - "loss": 5.2573, + "epoch": 0.95, + "learning_rate": 0.00012244897959183673, + "loss": 8.4938, "step": 846 }, { - "epoch": 0.47, - "learning_rate": 0.0007375389408099688, - "loss": 5.3203, + "epoch": 0.95, + "learning_rate": 0.00011989795918367347, + "loss": 4.594, "step": 847 }, { - "epoch": 0.48, - "learning_rate": 0.000736760124610592, - "loss": 5.631, + "epoch": 0.95, + "learning_rate": 0.00011734693877551021, + "loss": 5.1287, "step": 848 }, { - "epoch": 0.48, - "learning_rate": 0.000735981308411215, - "loss": 5.4784, + "epoch": 0.95, + "learning_rate": 0.00011479591836734695, + "loss": 4.8459, "step": 849 }, { - "epoch": 0.48, - "learning_rate": 0.000735202492211838, - "loss": 6.4499, + "epoch": 0.95, + "learning_rate": 0.00011224489795918367, + "loss": 4.7704, "step": 850 }, { - "epoch": 0.48, - "learning_rate": 0.0007344236760124611, - "loss": 7.6898, + "epoch": 0.95, + "learning_rate": 0.00010969387755102041, + "loss": 4.6765, "step": 851 }, { - "epoch": 0.48, - "learning_rate": 0.0007336448598130841, - "loss": 6.1893, + "epoch": 0.96, + "learning_rate": 0.00010714285714285714, + "loss": 4.9124, "step": 852 }, { - "epoch": 0.48, - "learning_rate": 0.0007328660436137072, - "loss": 5.7563, + "epoch": 0.96, + "learning_rate": 0.00010459183673469389, + "loss": 4.7199, "step": 853 }, { - "epoch": 0.48, - "learning_rate": 0.0007320872274143302, - "loss": 5.6705, + "epoch": 0.96, + "learning_rate": 0.00010204081632653062, + "loss": 4.6014, "step": 854 }, { - "epoch": 0.48, - "learning_rate": 0.0007313084112149533, - "loss": 5.624, + "epoch": 0.96, + "learning_rate": 9.948979591836734e-05, + "loss": 4.6581, "step": 855 }, { - "epoch": 0.48, - "learning_rate": 0.0007305295950155764, - "loss": 5.7006, + "epoch": 0.96, + "learning_rate": 9.693877551020408e-05, + "loss": 4.5992, "step": 856 }, { - "epoch": 0.48, - "learning_rate": 0.0007297507788161994, - "loss": 5.4542, + "epoch": 0.96, + "learning_rate": 9.438775510204081e-05, + "loss": 4.873, "step": 857 }, - { - "epoch": 0.48, - "learning_rate": 0.0007289719626168224, - "loss": 5.6944, - "step": 858 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007281931464174455, - "loss": 5.5975, - "step": 859 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007274143302180686, - "loss": 6.3941, - "step": 860 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007266355140186916, - "loss": 5.172, - "step": 861 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007258566978193146, - "loss": 5.32, - "step": 862 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007250778816199377, - "loss": 6.1573, - "step": 863 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007242990654205608, - "loss": 5.2023, - "step": 864 - }, - { - "epoch": 0.48, - "learning_rate": 0.0007235202492211839, - "loss": 6.2759, - "step": 865 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007227414330218068, - "loss": 5.6983, - "step": 866 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007219626168224299, - "loss": 5.4068, - "step": 867 - }, - { - "epoch": 0.49, - "learning_rate": 0.000721183800623053, - "loss": 5.6701, - "step": 868 - }, - { - "epoch": 0.49, - "learning_rate": 0.000720404984423676, - "loss": 5.5527, - "step": 869 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007196261682242991, - "loss": 5.4464, - "step": 870 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007188473520249221, - "loss": 5.5059, - "step": 871 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007180685358255452, - "loss": 5.5104, - "step": 872 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007172897196261683, - "loss": 5.5093, - "step": 873 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007165109034267912, - "loss": 5.3712, - "step": 874 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007157320872274144, - "loss": 5.7928, - "step": 875 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007149532710280374, - "loss": 5.617, - "step": 876 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007141744548286604, - "loss": 5.697, - "step": 877 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007133956386292835, - "loss": 5.3651, - "step": 878 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007126168224299065, - "loss": 5.3048, - "step": 879 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007118380062305297, - "loss": 5.6245, - "step": 880 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007110591900311527, - "loss": 5.4995, - "step": 881 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007102803738317756, - "loss": 5.1538, - "step": 882 - }, - { - "epoch": 0.49, - "learning_rate": 0.0007095015576323988, - "loss": 5.7107, - "step": 883 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007087227414330218, - "loss": 5.959, - "step": 884 - }, - { - "epoch": 0.5, - "learning_rate": 0.000707943925233645, - "loss": 6.1093, - "step": 885 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007071651090342679, - "loss": 5.596, - "step": 886 - }, - { - "epoch": 0.5, - "learning_rate": 0.000706386292834891, - "loss": 5.9195, - "step": 887 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007056074766355141, - "loss": 5.3348, - "step": 888 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007048286604361371, - "loss": 5.6177, - "step": 889 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007040498442367601, - "loss": 5.5897, - "step": 890 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007032710280373832, - "loss": 5.5187, - "step": 891 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007024922118380063, - "loss": 5.7876, - "step": 892 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007017133956386294, - "loss": 5.9358, - "step": 893 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007009345794392523, - "loss": 5.5355, - "step": 894 - }, - { - "epoch": 0.5, - "learning_rate": 0.0007001557632398754, - "loss": 5.3936, - "step": 895 - }, - { - "epoch": 0.5, - "learning_rate": 0.0006993769470404985, - "loss": 5.3101, - "step": 896 - }, - { - "epoch": 0.5, - "learning_rate": 0.0006985981308411216, - "loss": 5.4027, - "step": 897 - }, - { - "epoch": 0.5, - "learning_rate": 0.0006978193146417445, - "loss": 9.6362, - "step": 898 - }, - { - "epoch": 0.5, - "learning_rate": 0.0006970404984423676, - "loss": 7.056, - "step": 899 - }, - { - "epoch": 0.5, - "learning_rate": 0.0006962616822429907, - "loss": 8.4348, - "step": 900 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006954828660436138, - "loss": 5.419, - "step": 901 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006947040498442368, - "loss": 6.9592, - "step": 902 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006939252336448598, - "loss": 6.454, - "step": 903 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006931464174454829, - "loss": 5.9795, - "step": 904 - }, - { - "epoch": 0.51, - "learning_rate": 0.000692367601246106, - "loss": 5.9063, - "step": 905 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006915887850467289, - "loss": 5.8792, - "step": 906 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006908099688473521, - "loss": 6.1416, - "step": 907 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006900311526479751, - "loss": 5.3218, - "step": 908 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006892523364485982, - "loss": 5.9127, - "step": 909 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006884735202492212, - "loss": 5.4269, - "step": 910 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006876947040498442, - "loss": 6.1226, - "step": 911 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006869158878504674, - "loss": 5.3347, - "step": 912 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006861370716510904, - "loss": 5.7906, - "step": 913 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006853582554517133, - "loss": 5.5451, - "step": 914 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006845794392523365, - "loss": 5.8981, - "step": 915 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006838006230529595, - "loss": 6.239, - "step": 916 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006830218068535827, - "loss": 6.0943, - "step": 917 - }, - { - "epoch": 0.51, - "learning_rate": 0.0006822429906542056, - "loss": 6.4503, - "step": 918 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006814641744548286, - "loss": 5.8056, - "step": 919 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006806853582554518, - "loss": 5.0946, - "step": 920 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006799065420560748, - "loss": 5.3855, - "step": 921 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006791277258566978, - "loss": 5.7024, - "step": 922 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006783489096573209, - "loss": 5.3816, - "step": 923 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006775700934579439, - "loss": 5.4734, - "step": 924 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006767912772585671, - "loss": 5.8569, - "step": 925 - }, - { - "epoch": 0.52, - "learning_rate": 0.00067601246105919, - "loss": 5.8137, - "step": 926 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006752336448598131, - "loss": 5.2844, - "step": 927 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006744548286604362, - "loss": 5.343, - "step": 928 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006736760124610592, - "loss": 5.2121, - "step": 929 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006728971962616822, - "loss": 5.5872, - "step": 930 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006721183800623053, - "loss": 5.7077, - "step": 931 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006713395638629284, - "loss": 5.6032, - "step": 932 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006705607476635515, - "loss": 5.6579, - "step": 933 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006697819314641744, - "loss": 5.5783, - "step": 934 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006690031152647975, - "loss": 6.0164, - "step": 935 - }, - { - "epoch": 0.52, - "learning_rate": 0.0006682242990654206, - "loss": 5.5249, - "step": 936 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006674454828660437, - "loss": 5.5319, - "step": 937 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006666666666666666, - "loss": 5.1802, - "step": 938 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006658878504672897, - "loss": 5.3269, - "step": 939 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006651090342679128, - "loss": 5.659, - "step": 940 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006643302180685359, - "loss": 5.6678, - "step": 941 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006635514018691589, - "loss": 5.3538, - "step": 942 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006627725856697819, - "loss": 7.1806, - "step": 943 - }, - { - "epoch": 0.53, - "learning_rate": 0.000661993769470405, - "loss": 5.5311, - "step": 944 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006612149532710281, - "loss": 5.6919, - "step": 945 - }, - { - "epoch": 0.53, - "learning_rate": 0.000660436137071651, - "loss": 5.4196, - "step": 946 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006596573208722742, - "loss": 5.0956, - "step": 947 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006588785046728972, - "loss": 5.5857, - "step": 948 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006580996884735203, - "loss": 6.5744, - "step": 949 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006573208722741433, - "loss": 4.8242, - "step": 950 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006565420560747663, - "loss": 5.5892, - "step": 951 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006557632398753895, - "loss": 5.6456, - "step": 952 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006549844236760125, - "loss": 5.6, - "step": 953 - }, - { - "epoch": 0.53, - "learning_rate": 0.0006542056074766354, - "loss": 5.2075, - "step": 954 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006534267912772586, - "loss": 5.4556, - "step": 955 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006526479750778816, - "loss": 5.2723, - "step": 956 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006518691588785048, - "loss": 5.8474, - "step": 957 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006510903426791277, - "loss": 5.3051, - "step": 958 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006503115264797507, - "loss": 5.903, - "step": 959 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006495327102803739, - "loss": 5.5415, - "step": 960 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006487538940809969, - "loss": 5.2214, - "step": 961 - }, - { - "epoch": 0.54, - "learning_rate": 0.00064797507788162, - "loss": 5.3613, - "step": 962 - }, - { - "epoch": 0.54, - "learning_rate": 0.000647196261682243, - "loss": 6.6623, - "step": 963 - }, - { - "epoch": 0.54, - "learning_rate": 0.000646417445482866, - "loss": 5.357, - "step": 964 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006456386292834892, - "loss": 5.2329, - "step": 965 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006448598130841121, - "loss": 5.26, - "step": 966 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006440809968847352, - "loss": 6.0252, - "step": 967 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006433021806853583, - "loss": 5.4088, - "step": 968 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006425233644859813, - "loss": 5.4609, - "step": 969 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006417445482866044, - "loss": 5.2525, - "step": 970 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006409657320872274, - "loss": 5.3821, - "step": 971 - }, - { - "epoch": 0.54, - "learning_rate": 0.0006401869158878505, - "loss": 5.2642, - "step": 972 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006394080996884736, - "loss": 5.4046, - "step": 973 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006386292834890965, - "loss": 6.7089, - "step": 974 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006378504672897196, - "loss": 5.4015, - "step": 975 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006370716510903427, - "loss": 6.1485, - "step": 976 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006362928348909658, - "loss": 6.1073, - "step": 977 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006355140186915888, - "loss": 5.3363, - "step": 978 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006347352024922118, - "loss": 5.8938, - "step": 979 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006339563862928349, - "loss": 5.3889, - "step": 980 - }, - { - "epoch": 0.55, - "learning_rate": 0.000633177570093458, - "loss": 5.0848, - "step": 981 - }, - { - "epoch": 0.55, - "learning_rate": 0.000632398753894081, - "loss": 5.0785, - "step": 982 - }, - { - "epoch": 0.55, - "learning_rate": 0.000631619937694704, - "loss": 5.6771, - "step": 983 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006308411214953271, - "loss": 5.5653, - "step": 984 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006300623052959502, - "loss": 5.1484, - "step": 985 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006292834890965732, - "loss": 5.4235, - "step": 986 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006285046728971963, - "loss": 5.6977, - "step": 987 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006277258566978193, - "loss": 5.3653, - "step": 988 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006269470404984425, - "loss": 5.6545, - "step": 989 - }, - { - "epoch": 0.55, - "learning_rate": 0.0006261682242990654, - "loss": 5.1373, - "step": 990 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006253894080996884, - "loss": 5.5541, - "step": 991 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006246105919003116, - "loss": 5.776, - "step": 992 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006238317757009346, - "loss": 5.4849, - "step": 993 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006230529595015575, - "loss": 5.8827, - "step": 994 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006222741433021807, - "loss": 5.3848, - "step": 995 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006214953271028037, - "loss": 4.7318, - "step": 996 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006207165109034269, - "loss": 5.5799, - "step": 997 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006199376947040498, - "loss": 6.1309, - "step": 998 - }, - { - "epoch": 0.56, - "learning_rate": 0.000619158878504673, - "loss": 5.4247, - "step": 999 - }, - { - "epoch": 0.56, - "learning_rate": 0.000618380062305296, - "loss": 5.2015, - "step": 1000 - }, - { - "epoch": 0.56, - "eval_loss": 5.70602560043335, - "eval_runtime": 950.6376, - "eval_samples_per_second": 2.779, - "eval_steps_per_second": 0.348, - "eval_wer": 1.9426418088060293, - "step": 1000 - }, - { - "epoch": 0.56, - "learning_rate": 0.000617601246105919, - "loss": 5.6689, - "step": 1001 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006168224299065421, - "loss": 5.3031, - "step": 1002 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006160436137071651, - "loss": 5.4784, - "step": 1003 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006152647975077882, - "loss": 5.6971, - "step": 1004 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006144859813084113, - "loss": 5.4457, - "step": 1005 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006137071651090342, - "loss": 5.5111, - "step": 1006 - }, - { - "epoch": 0.56, - "learning_rate": 0.0006129283489096573, - "loss": 5.8861, - "step": 1007 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006121495327102804, - "loss": 6.1981, - "step": 1008 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006113707165109035, - "loss": 5.8416, - "step": 1009 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006105919003115265, - "loss": 5.2303, - "step": 1010 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006098130841121495, - "loss": 5.4072, - "step": 1011 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006090342679127726, - "loss": 5.5457, - "step": 1012 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006082554517133957, - "loss": 5.342, - "step": 1013 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006074766355140187, - "loss": 5.4438, - "step": 1014 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006066978193146417, - "loss": 5.7337, - "step": 1015 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006059190031152648, - "loss": 5.176, - "step": 1016 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006051401869158879, - "loss": 5.333, - "step": 1017 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006043613707165109, - "loss": 5.4578, - "step": 1018 - }, - { - "epoch": 0.57, - "learning_rate": 0.000603582554517134, - "loss": 6.7956, - "step": 1019 - }, - { - "epoch": 0.57, - "learning_rate": 0.000602803738317757, - "loss": 6.704, - "step": 1020 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006020249221183801, - "loss": 5.5269, - "step": 1021 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006012461059190031, - "loss": 5.4171, - "step": 1022 - }, - { - "epoch": 0.57, - "learning_rate": 0.0006004672897196261, - "loss": 5.5575, - "step": 1023 - }, - { - "epoch": 0.57, - "learning_rate": 0.0005996884735202493, - "loss": 5.5185, - "step": 1024 - }, - { - "epoch": 0.57, - "learning_rate": 0.0005989096573208723, - "loss": 6.033, - "step": 1025 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005981308411214953, - "loss": 5.2576, - "step": 1026 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005973520249221184, - "loss": 5.4374, - "step": 1027 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005965732087227414, - "loss": 5.7042, - "step": 1028 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005957943925233646, - "loss": 5.3615, - "step": 1029 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005950155763239875, - "loss": 5.45, - "step": 1030 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005942367601246105, - "loss": 5.6864, - "step": 1031 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005934579439252337, - "loss": 5.6557, - "step": 1032 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005926791277258567, - "loss": 5.2147, - "step": 1033 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005919003115264798, - "loss": 5.0558, - "step": 1034 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005911214953271028, - "loss": 5.3866, - "step": 1035 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005903426791277258, - "loss": 5.651, - "step": 1036 - }, - { - "epoch": 0.58, - "learning_rate": 0.000589563862928349, - "loss": 5.2983, - "step": 1037 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005887850467289719, - "loss": 5.4711, - "step": 1038 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005880062305295951, - "loss": 5.892, - "step": 1039 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005872274143302181, - "loss": 5.7102, - "step": 1040 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005864485981308411, - "loss": 5.4604, - "step": 1041 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005856697819314642, - "loss": 5.4072, - "step": 1042 - }, - { - "epoch": 0.58, - "learning_rate": 0.0005848909657320872, - "loss": 5.4335, - "step": 1043 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005841121495327103, - "loss": 5.9093, - "step": 1044 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005833333333333334, - "loss": 6.762, - "step": 1045 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005825545171339563, - "loss": 5.5875, - "step": 1046 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005817757009345795, - "loss": 5.5014, - "step": 1047 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005809968847352025, - "loss": 5.1769, - "step": 1048 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005802180685358256, - "loss": 5.9345, - "step": 1049 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005794392523364486, - "loss": 6.4257, - "step": 1050 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005786604361370716, - "loss": 6.7644, - "step": 1051 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005778816199376947, - "loss": 5.5467, - "step": 1052 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005771028037383178, - "loss": 5.2914, - "step": 1053 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005763239875389408, - "loss": 5.1816, - "step": 1054 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005755451713395639, - "loss": 5.6985, - "step": 1055 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005747663551401869, - "loss": 5.2733, - "step": 1056 - }, - { - "epoch": 0.59, - "learning_rate": 0.00057398753894081, - "loss": 6.0753, - "step": 1057 - }, - { - "epoch": 0.59, - "learning_rate": 0.000573208722741433, - "loss": 5.2696, - "step": 1058 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005724299065420561, - "loss": 6.3156, - "step": 1059 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005716510903426791, - "loss": 5.2567, - "step": 1060 - }, - { - "epoch": 0.59, - "learning_rate": 0.0005708722741433022, - "loss": 5.5776, - "step": 1061 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005700934579439252, - "loss": 5.3782, - "step": 1062 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005693146417445483, - "loss": 6.1488, - "step": 1063 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005685358255451714, - "loss": 5.036, - "step": 1064 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005677570093457944, - "loss": 6.0397, - "step": 1065 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005669781931464174, - "loss": 5.0347, - "step": 1066 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005661993769470405, - "loss": 5.4592, - "step": 1067 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005654205607476635, - "loss": 5.2184, - "step": 1068 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005646417445482867, - "loss": 5.3936, - "step": 1069 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005638629283489096, - "loss": 5.2781, - "step": 1070 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005630841121495327, - "loss": 5.2661, - "step": 1071 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005623052959501558, - "loss": 4.9864, - "step": 1072 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005615264797507788, - "loss": 5.2231, - "step": 1073 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005607476635514019, - "loss": 5.7709, - "step": 1074 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005599688473520249, - "loss": 5.5076, - "step": 1075 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005591900311526479, - "loss": 6.7439, - "step": 1076 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005584112149532711, - "loss": 5.4099, - "step": 1077 - }, - { - "epoch": 0.6, - "learning_rate": 0.000557632398753894, - "loss": 5.1565, - "step": 1078 - }, - { - "epoch": 0.6, - "learning_rate": 0.0005568535825545172, - "loss": 5.2359, - "step": 1079 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005560747663551402, - "loss": 5.6181, - "step": 1080 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005552959501557632, - "loss": 5.7145, - "step": 1081 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005545171339563863, - "loss": 5.5936, - "step": 1082 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005537383177570093, - "loss": 5.021, - "step": 1083 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005529595015576325, - "loss": 5.3595, - "step": 1084 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005521806853582555, - "loss": 5.1309, - "step": 1085 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005514018691588784, - "loss": 5.4788, - "step": 1086 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005506230529595016, - "loss": 5.5907, - "step": 1087 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005498442367601246, - "loss": 5.4964, - "step": 1088 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005490654205607477, - "loss": 5.6934, - "step": 1089 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005482866043613707, - "loss": 5.2149, - "step": 1090 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005475077881619937, - "loss": 5.2926, - "step": 1091 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005467289719626169, - "loss": 5.4489, - "step": 1092 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005459501557632399, - "loss": 5.3647, - "step": 1093 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005451713395638629, - "loss": 5.8544, - "step": 1094 - }, - { - "epoch": 0.61, - "learning_rate": 0.000544392523364486, - "loss": 5.4013, - "step": 1095 - }, - { - "epoch": 0.61, - "learning_rate": 0.000543613707165109, - "loss": 6.4426, - "step": 1096 - }, - { - "epoch": 0.61, - "learning_rate": 0.0005428348909657321, - "loss": 7.1915, - "step": 1097 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005420560747663551, - "loss": 6.4492, - "step": 1098 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005412772585669782, - "loss": 5.6389, - "step": 1099 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005404984423676013, - "loss": 6.342, - "step": 1100 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005397196261682244, - "loss": 5.19, - "step": 1101 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005389408099688473, - "loss": 5.4949, - "step": 1102 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005381619937694704, - "loss": 5.5425, - "step": 1103 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005373831775700935, - "loss": 5.1668, - "step": 1104 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005366043613707165, - "loss": 5.2455, - "step": 1105 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005358255451713396, - "loss": 5.004, - "step": 1106 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005350467289719626, - "loss": 5.6535, - "step": 1107 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005342679127725857, - "loss": 5.2132, - "step": 1108 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005334890965732088, - "loss": 5.2563, - "step": 1109 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005327102803738317, - "loss": 5.4135, - "step": 1110 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005319314641744549, - "loss": 5.4062, - "step": 1111 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005311526479750779, - "loss": 5.4272, - "step": 1112 - }, - { - "epoch": 0.62, - "learning_rate": 0.0005303738317757009, - "loss": 5.3793, - "step": 1113 - }, - { - "epoch": 0.62, - "learning_rate": 0.000529595015576324, - "loss": 6.0389, - "step": 1114 - }, - { - "epoch": 0.62, - "learning_rate": 0.000528816199376947, - "loss": 5.8371, - "step": 1115 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005280373831775702, - "loss": 5.0897, - "step": 1116 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005272585669781932, - "loss": 5.3767, - "step": 1117 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005264797507788161, - "loss": 5.542, - "step": 1118 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005257009345794393, - "loss": 5.3313, - "step": 1119 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005249221183800623, - "loss": 5.5115, - "step": 1120 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005241433021806854, - "loss": 5.3843, - "step": 1121 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005233644859813084, - "loss": 5.1503, - "step": 1122 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005225856697819314, - "loss": 5.4807, - "step": 1123 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005218068535825546, - "loss": 4.9823, - "step": 1124 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005210280373831776, - "loss": 5.5898, - "step": 1125 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005202492211838006, - "loss": 5.2799, - "step": 1126 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005194704049844237, - "loss": 5.1007, - "step": 1127 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005186915887850467, - "loss": 5.6326, - "step": 1128 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005179127725856698, - "loss": 4.9513, - "step": 1129 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005171339563862928, - "loss": 5.7074, - "step": 1130 - }, - { - "epoch": 0.63, - "learning_rate": 0.0005163551401869159, - "loss": 5.4049, - "step": 1131 - }, - { - "epoch": 0.63, - "learning_rate": 0.000515576323987539, - "loss": 5.3113, - "step": 1132 - }, - { - "epoch": 0.64, - "learning_rate": 0.000514797507788162, - "loss": 5.4968, - "step": 1133 - }, - { - "epoch": 0.64, - "learning_rate": 0.000514018691588785, - "loss": 5.1651, - "step": 1134 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005132398753894081, - "loss": 5.6117, - "step": 1135 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005124610591900312, - "loss": 4.9177, - "step": 1136 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005116822429906542, - "loss": 5.5667, - "step": 1137 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005109034267912772, - "loss": 5.3672, - "step": 1138 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005101246105919003, - "loss": 5.0054, - "step": 1139 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005093457943925234, - "loss": 5.1498, - "step": 1140 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005085669781931465, - "loss": 5.28, - "step": 1141 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005077881619937694, - "loss": 5.9577, - "step": 1142 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005070093457943925, - "loss": 6.6298, - "step": 1143 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005062305295950156, - "loss": 5.4758, - "step": 1144 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005054517133956386, - "loss": 5.1052, - "step": 1145 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005046728971962617, - "loss": 5.4622, - "step": 1146 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005038940809968847, - "loss": 5.4579, - "step": 1147 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005031152647975078, - "loss": 5.3735, - "step": 1148 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005023364485981309, - "loss": 6.0667, - "step": 1149 - }, - { - "epoch": 0.64, - "learning_rate": 0.0005015576323987538, - "loss": 5.0684, - "step": 1150 - }, - { - "epoch": 0.65, - "learning_rate": 0.000500778816199377, - "loss": 5.6995, - "step": 1151 - }, - { - "epoch": 0.65, - "learning_rate": 0.0005, - "loss": 5.5138, - "step": 1152 - }, - { - "epoch": 0.65, - "learning_rate": 0.000499221183800623, - "loss": 5.2717, - "step": 1153 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004984423676012461, - "loss": 5.3284, - "step": 1154 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004976635514018692, - "loss": 5.4072, - "step": 1155 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004968847352024923, - "loss": 5.4622, - "step": 1156 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004961059190031153, - "loss": 5.2763, - "step": 1157 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004953271028037383, - "loss": 5.339, - "step": 1158 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004945482866043614, - "loss": 5.1403, - "step": 1159 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004937694704049844, - "loss": 5.0255, - "step": 1160 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004929906542056076, - "loss": 5.2258, - "step": 1161 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004922118380062306, - "loss": 5.1121, - "step": 1162 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004914330218068536, - "loss": 5.2466, - "step": 1163 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004906542056074767, - "loss": 4.9286, - "step": 1164 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004898753894080997, - "loss": 5.0602, - "step": 1165 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004890965732087227, - "loss": 5.3484, - "step": 1166 - }, - { - "epoch": 0.65, - "learning_rate": 0.0004883177570093459, - "loss": 5.6595, - "step": 1167 - }, - { - "epoch": 0.65, - "learning_rate": 0.00048753894080996886, - "loss": 4.9488, - "step": 1168 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048676012461059195, - "loss": 5.2174, - "step": 1169 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048598130841121494, - "loss": 5.3447, - "step": 1170 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048520249221183803, - "loss": 5.431, - "step": 1171 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048442367601246106, - "loss": 4.8908, - "step": 1172 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048364485981308415, - "loss": 5.828, - "step": 1173 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004828660436137072, - "loss": 5.0935, - "step": 1174 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004820872274143302, - "loss": 5.4501, - "step": 1175 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048130841121495326, - "loss": 5.6197, - "step": 1176 - }, - { - "epoch": 0.66, - "learning_rate": 0.00048052959501557635, - "loss": 5.1815, - "step": 1177 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004797507788161994, - "loss": 5.4918, - "step": 1178 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004789719626168225, - "loss": 4.9793, - "step": 1179 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004781931464174455, - "loss": 5.2911, - "step": 1180 - }, - { - "epoch": 0.66, - "learning_rate": 0.00047741433021806855, - "loss": 5.0939, - "step": 1181 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004766355140186916, - "loss": 5.5437, - "step": 1182 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004758566978193147, - "loss": 5.3463, - "step": 1183 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004750778816199377, - "loss": 5.0653, - "step": 1184 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004742990654205608, - "loss": 5.6993, - "step": 1185 - }, - { - "epoch": 0.66, - "learning_rate": 0.0004735202492211838, - "loss": 5.1006, - "step": 1186 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004727414330218069, - "loss": 5.3518, - "step": 1187 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004719626168224299, - "loss": 5.4126, - "step": 1188 - }, - { - "epoch": 0.67, - "learning_rate": 0.000471183800623053, - "loss": 5.2392, - "step": 1189 - }, - { - "epoch": 0.67, - "learning_rate": 0.00047040498442367604, - "loss": 5.1928, - "step": 1190 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004696261682242991, - "loss": 5.2106, - "step": 1191 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004688473520249221, - "loss": 5.5965, - "step": 1192 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004680685358255452, - "loss": 5.6314, - "step": 1193 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046728971962616824, - "loss": 5.3374, - "step": 1194 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046651090342679133, - "loss": 5.1681, - "step": 1195 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004657320872274143, - "loss": 4.8921, - "step": 1196 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004649532710280374, - "loss": 5.129, - "step": 1197 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046417445482866044, - "loss": 5.2794, - "step": 1198 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046339563862928353, - "loss": 5.2482, - "step": 1199 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046261682242990657, - "loss": 4.7676, - "step": 1200 - }, - { - "epoch": 0.67, - "learning_rate": 0.0004618380062305296, - "loss": 5.2866, - "step": 1201 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046105919003115264, - "loss": 5.1343, - "step": 1202 - }, - { - "epoch": 0.67, - "learning_rate": 0.00046028037383177573, - "loss": 5.1511, - "step": 1203 - }, - { - "epoch": 0.67, - "learning_rate": 0.00045950155763239877, - "loss": 5.0781, - "step": 1204 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045872274143302186, - "loss": 4.9903, - "step": 1205 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045794392523364484, - "loss": 5.1752, - "step": 1206 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045716510903426793, - "loss": 6.1712, - "step": 1207 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045638629283489097, - "loss": 5.351, - "step": 1208 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045560747663551406, - "loss": 5.2055, - "step": 1209 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004548286604361371, - "loss": 5.2923, - "step": 1210 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045404984423676013, - "loss": 5.6708, - "step": 1211 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045327102803738317, - "loss": 5.5055, - "step": 1212 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045249221183800626, - "loss": 5.2497, - "step": 1213 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004517133956386293, - "loss": 5.3091, - "step": 1214 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004509345794392524, - "loss": 5.2832, - "step": 1215 - }, - { - "epoch": 0.68, - "learning_rate": 0.00045015576323987537, - "loss": 5.3384, - "step": 1216 - }, - { - "epoch": 0.68, - "learning_rate": 0.00044937694704049846, - "loss": 5.0263, - "step": 1217 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004485981308411215, - "loss": 4.8196, - "step": 1218 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004478193146417446, - "loss": 5.0165, - "step": 1219 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004470404984423676, - "loss": 5.5021, - "step": 1220 - }, - { - "epoch": 0.68, - "learning_rate": 0.00044626168224299066, - "loss": 5.0788, - "step": 1221 - }, - { - "epoch": 0.68, - "learning_rate": 0.0004454828660436137, - "loss": 6.076, - "step": 1222 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004447040498442368, - "loss": 5.3081, - "step": 1223 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004439252336448598, - "loss": 5.4505, - "step": 1224 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004431464174454829, - "loss": 5.802, - "step": 1225 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004423676012461059, - "loss": 5.1533, - "step": 1226 - }, - { - "epoch": 0.69, - "learning_rate": 0.000441588785046729, - "loss": 5.0714, - "step": 1227 - }, - { - "epoch": 0.69, - "learning_rate": 0.000440809968847352, - "loss": 5.0941, - "step": 1228 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004400311526479751, - "loss": 5.1219, - "step": 1229 - }, - { - "epoch": 0.69, - "learning_rate": 0.00043925233644859815, - "loss": 5.6856, - "step": 1230 - }, - { - "epoch": 0.69, - "learning_rate": 0.00043847352024922124, - "loss": 5.1848, - "step": 1231 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004376947040498442, - "loss": 5.313, - "step": 1232 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004369158878504673, - "loss": 5.3238, - "step": 1233 - }, - { - "epoch": 0.69, - "learning_rate": 0.00043613707165109035, - "loss": 5.0253, - "step": 1234 - }, - { - "epoch": 0.69, - "learning_rate": 0.00043535825545171344, - "loss": 5.6019, - "step": 1235 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004345794392523365, - "loss": 5.2683, - "step": 1236 - }, - { - "epoch": 0.69, - "learning_rate": 0.0004338006230529595, - "loss": 5.5906, - "step": 1237 - }, - { - "epoch": 0.69, - "learning_rate": 0.00043302180685358255, - "loss": 5.0926, - "step": 1238 - }, - { - "epoch": 0.69, - "learning_rate": 0.00043224299065420564, - "loss": 6.2024, - "step": 1239 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004314641744548287, - "loss": 5.5247, - "step": 1240 - }, - { - "epoch": 0.7, - "learning_rate": 0.00043068535825545177, - "loss": 5.1037, - "step": 1241 - }, - { - "epoch": 0.7, - "learning_rate": 0.00042990654205607475, - "loss": 5.6154, - "step": 1242 - }, - { - "epoch": 0.7, - "learning_rate": 0.00042912772585669784, - "loss": 5.2992, - "step": 1243 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004283489096573209, - "loss": 5.1898, - "step": 1244 - }, - { - "epoch": 0.7, - "learning_rate": 0.00042757009345794397, - "loss": 4.7974, - "step": 1245 - }, - { - "epoch": 0.7, - "learning_rate": 0.000426791277258567, - "loss": 5.3809, - "step": 1246 - }, - { - "epoch": 0.7, - "learning_rate": 0.00042601246105919004, - "loss": 5.4442, - "step": 1247 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004252336448598131, - "loss": 5.2653, - "step": 1248 - }, - { - "epoch": 0.7, - "learning_rate": 0.00042445482866043617, - "loss": 5.3378, - "step": 1249 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004236760124610592, - "loss": 5.5524, - "step": 1250 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004228971962616823, - "loss": 5.3266, - "step": 1251 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004221183800623053, - "loss": 5.253, - "step": 1252 - }, - { - "epoch": 0.7, - "learning_rate": 0.00042133956386292837, - "loss": 5.3197, - "step": 1253 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004205607476635514, - "loss": 5.2668, - "step": 1254 - }, - { - "epoch": 0.7, - "learning_rate": 0.0004197819314641745, - "loss": 5.8363, - "step": 1255 - }, - { - "epoch": 0.7, - "learning_rate": 0.00041900311526479753, - "loss": 5.1588, - "step": 1256 - }, - { - "epoch": 0.7, - "learning_rate": 0.00041822429906542057, - "loss": 5.038, - "step": 1257 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004174454828660436, - "loss": 5.0357, - "step": 1258 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004166666666666667, - "loss": 5.1476, - "step": 1259 - }, - { - "epoch": 0.71, - "learning_rate": 0.00041588785046728973, - "loss": 5.5123, - "step": 1260 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004151090342679128, - "loss": 4.9036, - "step": 1261 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004143302180685358, - "loss": 5.2043, - "step": 1262 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004135514018691589, - "loss": 5.1004, - "step": 1263 - }, - { - "epoch": 0.71, - "learning_rate": 0.00041277258566978193, - "loss": 5.0777, - "step": 1264 - }, - { - "epoch": 0.71, - "learning_rate": 0.000411993769470405, - "loss": 5.656, - "step": 1265 - }, - { - "epoch": 0.71, - "learning_rate": 0.00041121495327102806, - "loss": 5.2757, - "step": 1266 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004104361370716511, - "loss": 5.3096, - "step": 1267 - }, - { - "epoch": 0.71, - "learning_rate": 0.00040965732087227413, - "loss": 5.139, - "step": 1268 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004088785046728972, - "loss": 5.1185, - "step": 1269 - }, - { - "epoch": 0.71, - "learning_rate": 0.00040809968847352026, - "loss": 5.1348, - "step": 1270 - }, - { - "epoch": 0.71, - "learning_rate": 0.00040732087227414335, - "loss": 5.4783, - "step": 1271 - }, - { - "epoch": 0.71, - "learning_rate": 0.00040654205607476633, - "loss": 5.0154, - "step": 1272 - }, - { - "epoch": 0.71, - "learning_rate": 0.0004057632398753894, - "loss": 5.2961, - "step": 1273 - }, - { - "epoch": 0.71, - "learning_rate": 0.00040498442367601246, - "loss": 5.0439, - "step": 1274 - }, - { - "epoch": 0.71, - "learning_rate": 0.00040420560747663555, - "loss": 5.3444, - "step": 1275 - }, - { - "epoch": 0.72, - "learning_rate": 0.0004034267912772586, - "loss": 5.84, - "step": 1276 - }, - { - "epoch": 0.72, - "learning_rate": 0.0004026479750778816, - "loss": 5.3709, - "step": 1277 - }, - { - "epoch": 0.72, - "learning_rate": 0.00040186915887850466, - "loss": 5.151, - "step": 1278 - }, - { - "epoch": 0.72, - "learning_rate": 0.00040109034267912775, - "loss": 5.7002, - "step": 1279 - }, - { - "epoch": 0.72, - "learning_rate": 0.0004003115264797508, - "loss": 5.2425, - "step": 1280 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003995327102803739, - "loss": 4.9711, - "step": 1281 - }, - { - "epoch": 0.72, - "learning_rate": 0.00039875389408099686, - "loss": 5.1147, - "step": 1282 - }, - { - "epoch": 0.72, - "learning_rate": 0.00039797507788161995, - "loss": 5.3042, - "step": 1283 - }, - { - "epoch": 0.72, - "learning_rate": 0.000397196261682243, - "loss": 5.04, - "step": 1284 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003964174454828661, - "loss": 5.0492, - "step": 1285 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003956386292834891, - "loss": 5.2488, - "step": 1286 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003948598130841122, - "loss": 5.0677, - "step": 1287 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003940809968847352, - "loss": 5.0325, - "step": 1288 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003933021806853583, - "loss": 5.0861, - "step": 1289 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003925233644859813, - "loss": 4.9365, - "step": 1290 - }, - { - "epoch": 0.72, - "learning_rate": 0.0003917445482866044, - "loss": 5.1791, - "step": 1291 - }, - { - "epoch": 0.72, - "learning_rate": 0.00039096573208722744, - "loss": 5.8415, - "step": 1292 - }, - { - "epoch": 0.72, - "learning_rate": 0.00039018691588785047, - "loss": 6.9251, - "step": 1293 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003894080996884735, - "loss": 4.912, - "step": 1294 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003886292834890966, - "loss": 4.8009, - "step": 1295 - }, - { - "epoch": 0.73, - "learning_rate": 0.00038785046728971964, - "loss": 4.7569, - "step": 1296 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003870716510903427, - "loss": 4.7809, - "step": 1297 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003862928348909657, - "loss": 4.7134, - "step": 1298 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003855140186915888, - "loss": 6.8767, - "step": 1299 - }, - { - "epoch": 0.73, - "learning_rate": 0.00038473520249221184, - "loss": 4.7278, - "step": 1300 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003839563862928349, - "loss": 5.4747, - "step": 1301 - }, - { - "epoch": 0.73, - "learning_rate": 0.00038317757009345796, - "loss": 5.598, - "step": 1302 - }, - { - "epoch": 0.73, - "learning_rate": 0.000382398753894081, - "loss": 5.3053, - "step": 1303 - }, - { - "epoch": 0.73, - "learning_rate": 0.00038161993769470404, - "loss": 5.2799, - "step": 1304 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003808411214953271, - "loss": 5.0743, - "step": 1305 - }, - { - "epoch": 0.73, - "learning_rate": 0.00038006230529595016, - "loss": 5.528, - "step": 1306 - }, - { - "epoch": 0.73, - "learning_rate": 0.00037928348909657325, - "loss": 5.0027, - "step": 1307 - }, - { - "epoch": 0.73, - "learning_rate": 0.00037850467289719624, - "loss": 4.9218, - "step": 1308 - }, - { - "epoch": 0.73, - "learning_rate": 0.0003777258566978193, - "loss": 5.0712, - "step": 1309 - }, - { - "epoch": 0.73, - "learning_rate": 0.00037694704049844236, - "loss": 5.0798, - "step": 1310 - }, - { - "epoch": 0.73, - "learning_rate": 0.00037616822429906545, - "loss": 4.902, - "step": 1311 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003753894080996885, - "loss": 5.2403, - "step": 1312 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003746105919003115, - "loss": 5.0167, - "step": 1313 - }, - { - "epoch": 0.74, - "learning_rate": 0.00037383177570093456, - "loss": 4.8196, - "step": 1314 - }, - { - "epoch": 0.74, - "learning_rate": 0.00037305295950155765, - "loss": 5.4405, - "step": 1315 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003722741433021807, - "loss": 5.1912, - "step": 1316 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003714953271028038, - "loss": 4.9177, - "step": 1317 - }, - { - "epoch": 0.74, - "learning_rate": 0.00037071651090342676, - "loss": 5.4692, - "step": 1318 - }, - { - "epoch": 0.74, - "learning_rate": 0.00036993769470404985, - "loss": 4.9422, - "step": 1319 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003691588785046729, - "loss": 4.8214, - "step": 1320 - }, - { - "epoch": 0.74, - "learning_rate": 0.000368380062305296, - "loss": 4.8067, - "step": 1321 - }, - { - "epoch": 0.74, - "learning_rate": 0.000367601246105919, - "loss": 5.1206, - "step": 1322 - }, - { - "epoch": 0.74, - "learning_rate": 0.00036682242990654205, - "loss": 5.4765, - "step": 1323 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003660436137071651, - "loss": 5.0346, - "step": 1324 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003652647975077882, - "loss": 5.0606, - "step": 1325 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003644859813084112, - "loss": 4.9586, - "step": 1326 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003637071651090343, - "loss": 4.7342, - "step": 1327 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003629283489096573, - "loss": 5.2514, - "step": 1328 - }, - { - "epoch": 0.74, - "learning_rate": 0.0003621495327102804, - "loss": 5.3119, - "step": 1329 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003613707165109034, - "loss": 5.1475, - "step": 1330 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003605919003115265, - "loss": 4.7475, - "step": 1331 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035981308411214954, - "loss": 5.1917, - "step": 1332 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003590342679127726, - "loss": 5.3058, - "step": 1333 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003582554517133956, - "loss": 5.3751, - "step": 1334 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003574766355140187, - "loss": 4.878, - "step": 1335 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035669781931464174, - "loss": 5.1347, - "step": 1336 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035591900311526483, - "loss": 5.1854, - "step": 1337 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003551401869158878, - "loss": 5.0367, - "step": 1338 - }, - { - "epoch": 0.75, - "learning_rate": 0.0003543613707165109, - "loss": 5.2869, - "step": 1339 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035358255451713394, - "loss": 5.4792, - "step": 1340 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035280373831775703, - "loss": 5.4281, - "step": 1341 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035202492211838007, - "loss": 5.2691, - "step": 1342 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035124610591900316, - "loss": 5.3289, - "step": 1343 - }, - { - "epoch": 0.75, - "learning_rate": 0.00035046728971962614, - "loss": 5.6491, - "step": 1344 - }, - { - "epoch": 0.75, - "learning_rate": 0.00034968847352024923, - "loss": 5.2183, - "step": 1345 - }, - { - "epoch": 0.75, - "learning_rate": 0.00034890965732087227, - "loss": 5.1053, - "step": 1346 - }, - { - "epoch": 0.76, - "learning_rate": 0.00034813084112149536, - "loss": 5.8315, - "step": 1347 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003473520249221184, - "loss": 4.9135, - "step": 1348 - }, - { - "epoch": 0.76, - "learning_rate": 0.00034657320872274143, - "loss": 5.2811, - "step": 1349 - }, - { - "epoch": 0.76, - "learning_rate": 0.00034579439252336447, - "loss": 4.8756, - "step": 1350 - }, - { - "epoch": 0.76, - "learning_rate": 0.00034501557632398756, - "loss": 5.2873, - "step": 1351 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003442367601246106, - "loss": 5.3054, - "step": 1352 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003434579439252337, - "loss": 5.221, - "step": 1353 - }, - { - "epoch": 0.76, - "learning_rate": 0.00034267912772585667, - "loss": 5.3471, - "step": 1354 - }, - { - "epoch": 0.76, - "learning_rate": 0.00034190031152647976, - "loss": 4.9741, - "step": 1355 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003411214953271028, - "loss": 5.2424, - "step": 1356 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003403426791277259, - "loss": 4.745, - "step": 1357 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003395638629283489, - "loss": 5.2385, - "step": 1358 - }, - { - "epoch": 0.76, - "learning_rate": 0.00033878504672897196, - "loss": 5.1884, - "step": 1359 - }, - { - "epoch": 0.76, - "learning_rate": 0.000338006230529595, - "loss": 5.5997, - "step": 1360 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003372274143302181, - "loss": 4.9694, - "step": 1361 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003364485981308411, - "loss": 4.9506, - "step": 1362 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003356697819314642, - "loss": 5.1342, - "step": 1363 - }, - { - "epoch": 0.76, - "learning_rate": 0.0003348909657320872, - "loss": 5.5148, - "step": 1364 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003341121495327103, - "loss": 5.5671, - "step": 1365 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003333333333333333, - "loss": 4.9106, - "step": 1366 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003325545171339564, - "loss": 5.0792, - "step": 1367 - }, - { - "epoch": 0.77, - "learning_rate": 0.00033177570093457945, - "loss": 4.9258, - "step": 1368 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003309968847352025, - "loss": 5.1372, - "step": 1369 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003302180685358255, - "loss": 5.1357, - "step": 1370 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003294392523364486, - "loss": 5.2378, - "step": 1371 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032866043613707165, - "loss": 4.8684, - "step": 1372 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032788161993769474, - "loss": 5.5748, - "step": 1373 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003271028037383177, - "loss": 5.237, - "step": 1374 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003263239875389408, - "loss": 5.2246, - "step": 1375 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032554517133956385, - "loss": 4.8544, - "step": 1376 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032476635514018694, - "loss": 5.5553, - "step": 1377 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032398753894081, - "loss": 5.15, - "step": 1378 - }, - { - "epoch": 0.77, - "learning_rate": 0.000323208722741433, - "loss": 4.9185, - "step": 1379 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032242990654205605, - "loss": 5.0296, - "step": 1380 - }, - { - "epoch": 0.77, - "learning_rate": 0.00032165109034267914, - "loss": 4.6631, - "step": 1381 - }, - { - "epoch": 0.77, - "learning_rate": 0.0003208722741433022, - "loss": 5.1008, - "step": 1382 - }, - { - "epoch": 0.78, - "learning_rate": 0.00032009345794392527, - "loss": 5.4328, - "step": 1383 - }, - { - "epoch": 0.78, - "learning_rate": 0.00031931464174454825, - "loss": 5.1655, - "step": 1384 - }, - { - "epoch": 0.78, - "learning_rate": 0.00031853582554517134, - "loss": 5.3209, - "step": 1385 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003177570093457944, - "loss": 5.0537, - "step": 1386 - }, - { - "epoch": 0.78, - "learning_rate": 0.00031697819314641747, - "loss": 5.225, - "step": 1387 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003161993769470405, - "loss": 5.1807, - "step": 1388 - }, - { - "epoch": 0.78, - "learning_rate": 0.00031542056074766354, - "loss": 4.9623, - "step": 1389 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003146417445482866, - "loss": 5.2131, - "step": 1390 - }, - { - "epoch": 0.78, - "learning_rate": 0.00031386292834890967, - "loss": 4.8298, - "step": 1391 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003130841121495327, - "loss": 4.8277, - "step": 1392 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003123052959501558, - "loss": 4.9371, - "step": 1393 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003115264797507788, - "loss": 5.4274, - "step": 1394 - }, - { - "epoch": 0.78, - "learning_rate": 0.00031074766355140187, - "loss": 6.5958, - "step": 1395 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003099688473520249, - "loss": 4.8895, - "step": 1396 - }, - { - "epoch": 0.78, - "learning_rate": 0.000309190031152648, - "loss": 5.0801, - "step": 1397 - }, - { - "epoch": 0.78, - "learning_rate": 0.00030841121495327103, - "loss": 4.7773, - "step": 1398 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003076323987538941, - "loss": 5.0562, - "step": 1399 - }, - { - "epoch": 0.78, - "learning_rate": 0.0003068535825545171, - "loss": 5.035, - "step": 1400 - }, - { - "epoch": 0.79, - "learning_rate": 0.0003060747663551402, - "loss": 4.8889, - "step": 1401 - }, - { - "epoch": 0.79, - "learning_rate": 0.00030529595015576323, - "loss": 5.2789, - "step": 1402 - }, - { - "epoch": 0.79, - "learning_rate": 0.0003045171339563863, - "loss": 4.9681, - "step": 1403 - }, - { - "epoch": 0.79, - "learning_rate": 0.00030373831775700936, - "loss": 4.973, - "step": 1404 - }, - { - "epoch": 0.79, - "learning_rate": 0.0003029595015576324, - "loss": 5.4689, - "step": 1405 - }, - { - "epoch": 0.79, - "learning_rate": 0.00030218068535825543, - "loss": 6.2559, - "step": 1406 - }, - { - "epoch": 0.79, - "learning_rate": 0.0003014018691588785, - "loss": 5.0098, - "step": 1407 - }, - { - "epoch": 0.79, - "learning_rate": 0.00030062305295950156, - "loss": 5.4956, - "step": 1408 - }, - { - "epoch": 0.79, - "learning_rate": 0.00029984423676012465, - "loss": 5.0559, - "step": 1409 - }, - { - "epoch": 0.79, - "learning_rate": 0.00029906542056074763, - "loss": 4.87, - "step": 1410 - }, - { - "epoch": 0.79, - "learning_rate": 0.0002982866043613707, - "loss": 4.9184, - "step": 1411 - }, - { - "epoch": 0.79, - "learning_rate": 0.00029750778816199376, - "loss": 4.8348, - "step": 1412 - }, - { - "epoch": 0.79, - "learning_rate": 0.00029672897196261685, - "loss": 5.2519, - "step": 1413 - }, - { - "epoch": 0.79, - "learning_rate": 0.0002959501557632399, - "loss": 5.4589, - "step": 1414 - }, - { - "epoch": 0.79, - "learning_rate": 0.0002951713395638629, - "loss": 5.0411, - "step": 1415 - }, - { - "epoch": 0.79, - "learning_rate": 0.00029439252336448596, - "loss": 5.2926, - "step": 1416 - }, - { - "epoch": 0.79, - "learning_rate": 0.00029361370716510905, - "loss": 5.1757, - "step": 1417 - }, - { - "epoch": 0.79, - "learning_rate": 0.0002928348909657321, - "loss": 5.6576, - "step": 1418 - }, - { - "epoch": 0.8, - "learning_rate": 0.00029205607476635517, - "loss": 5.2062, - "step": 1419 - }, - { - "epoch": 0.8, - "learning_rate": 0.00029127725856697815, - "loss": 4.8022, - "step": 1420 - }, - { - "epoch": 0.8, - "learning_rate": 0.00029049844236760125, - "loss": 5.2796, - "step": 1421 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002897196261682243, - "loss": 5.1439, - "step": 1422 - }, - { - "epoch": 0.8, - "learning_rate": 0.00028894080996884737, - "loss": 4.919, - "step": 1423 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002881619937694704, - "loss": 5.0736, - "step": 1424 - }, - { - "epoch": 0.8, - "learning_rate": 0.00028738317757009345, - "loss": 5.4473, - "step": 1425 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002866043613707165, - "loss": 5.3029, - "step": 1426 - }, - { - "epoch": 0.8, - "learning_rate": 0.00028582554517133957, - "loss": 4.8075, - "step": 1427 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002850467289719626, - "loss": 5.1271, - "step": 1428 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002842679127725857, - "loss": 5.3454, - "step": 1429 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002834890965732087, - "loss": 5.6479, - "step": 1430 - }, - { - "epoch": 0.8, - "learning_rate": 0.00028271028037383177, - "loss": 5.7627, - "step": 1431 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002819314641744548, - "loss": 5.2682, - "step": 1432 - }, - { - "epoch": 0.8, - "learning_rate": 0.0002811526479750779, - "loss": 5.3451, - "step": 1433 - }, - { - "epoch": 0.8, - "learning_rate": 0.00028037383177570094, - "loss": 4.9721, - "step": 1434 - }, - { - "epoch": 0.8, - "learning_rate": 0.00027959501557632397, - "loss": 5.248, - "step": 1435 - }, - { - "epoch": 0.8, - "learning_rate": 0.000278816199376947, - "loss": 4.8125, - "step": 1436 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002780373831775701, - "loss": 5.2279, - "step": 1437 - }, - { - "epoch": 0.81, - "learning_rate": 0.00027725856697819314, - "loss": 4.9584, - "step": 1438 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002764797507788162, - "loss": 5.0411, - "step": 1439 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002757009345794392, - "loss": 5.1293, - "step": 1440 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002749221183800623, - "loss": 5.5773, - "step": 1441 - }, - { - "epoch": 0.81, - "learning_rate": 0.00027414330218068533, - "loss": 4.9859, - "step": 1442 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002733644859813084, - "loss": 4.9418, - "step": 1443 - }, - { - "epoch": 0.81, - "learning_rate": 0.00027258566978193146, - "loss": 4.8131, - "step": 1444 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002718068535825545, - "loss": 5.0327, - "step": 1445 - }, - { - "epoch": 0.81, - "learning_rate": 0.00027102803738317753, - "loss": 5.4596, - "step": 1446 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002702492211838006, - "loss": 5.2024, - "step": 1447 - }, - { - "epoch": 0.81, - "learning_rate": 0.00026947040498442366, - "loss": 4.9302, - "step": 1448 - }, - { - "epoch": 0.81, - "learning_rate": 0.00026869158878504675, - "loss": 5.1619, - "step": 1449 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002679127725856698, - "loss": 4.9458, - "step": 1450 - }, - { - "epoch": 0.81, - "learning_rate": 0.0002671339563862928, - "loss": 5.098, - "step": 1451 - }, - { - "epoch": 0.81, - "learning_rate": 0.00026635514018691586, - "loss": 5.0626, - "step": 1452 - }, - { - "epoch": 0.81, - "learning_rate": 0.00026557632398753895, - "loss": 4.8657, - "step": 1453 - }, - { - "epoch": 0.82, - "learning_rate": 0.000264797507788162, - "loss": 4.8222, - "step": 1454 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002640186915887851, - "loss": 5.1035, - "step": 1455 - }, - { - "epoch": 0.82, - "learning_rate": 0.00026323987538940806, - "loss": 5.3281, - "step": 1456 - }, - { - "epoch": 0.82, - "learning_rate": 0.00026246105919003115, - "loss": 5.3442, - "step": 1457 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002616822429906542, - "loss": 5.2567, - "step": 1458 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002609034267912773, - "loss": 5.1102, - "step": 1459 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002601246105919003, - "loss": 5.5696, - "step": 1460 - }, - { - "epoch": 0.82, - "learning_rate": 0.00025934579439252335, - "loss": 4.9823, - "step": 1461 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002585669781931464, - "loss": 5.1301, - "step": 1462 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002577881619937695, - "loss": 4.8129, - "step": 1463 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002570093457943925, - "loss": 4.921, - "step": 1464 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002562305295950156, - "loss": 5.3481, - "step": 1465 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002554517133956386, - "loss": 5.0102, - "step": 1466 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002546728971962617, - "loss": 5.1034, - "step": 1467 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002538940809968847, - "loss": 4.9912, - "step": 1468 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002531152647975078, - "loss": 4.7331, - "step": 1469 - }, - { - "epoch": 0.82, - "learning_rate": 0.00025233644859813084, - "loss": 4.7302, - "step": 1470 - }, - { - "epoch": 0.82, - "learning_rate": 0.0002515576323987539, - "loss": 5.168, - "step": 1471 - }, - { - "epoch": 0.83, - "learning_rate": 0.0002507788161993769, - "loss": 4.7642, - "step": 1472 - }, - { - "epoch": 0.83, - "learning_rate": 0.00025, - "loss": 4.8919, - "step": 1473 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024922118380062304, - "loss": 4.7344, - "step": 1474 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024844236760124613, - "loss": 5.0241, - "step": 1475 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024766355140186917, - "loss": 5.1813, - "step": 1476 - }, - { - "epoch": 0.83, - "learning_rate": 0.0002468847352024922, - "loss": 5.2876, - "step": 1477 - }, - { - "epoch": 0.83, - "learning_rate": 0.0002461059190031153, - "loss": 4.6418, - "step": 1478 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024532710280373833, - "loss": 5.0075, - "step": 1479 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024454828660436137, - "loss": 4.7538, - "step": 1480 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024376947040498443, - "loss": 4.9763, - "step": 1481 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024299065420560747, - "loss": 5.5776, - "step": 1482 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024221183800623053, - "loss": 5.0527, - "step": 1483 - }, - { - "epoch": 0.83, - "learning_rate": 0.0002414330218068536, - "loss": 4.5475, - "step": 1484 - }, - { - "epoch": 0.83, - "learning_rate": 0.00024065420560747663, - "loss": 4.9443, - "step": 1485 - }, - { - "epoch": 0.83, - "learning_rate": 0.0002398753894080997, - "loss": 5.1981, - "step": 1486 - }, - { - "epoch": 0.83, - "learning_rate": 0.00023909657320872276, - "loss": 5.161, - "step": 1487 - }, - { - "epoch": 0.83, - "learning_rate": 0.0002383177570093458, - "loss": 5.1616, - "step": 1488 - }, - { - "epoch": 0.83, - "learning_rate": 0.00023753894080996886, - "loss": 5.1021, - "step": 1489 - }, - { - "epoch": 0.84, - "learning_rate": 0.0002367601246105919, - "loss": 4.789, - "step": 1490 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023598130841121496, - "loss": 5.3496, - "step": 1491 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023520249221183802, - "loss": 5.1104, - "step": 1492 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023442367601246106, - "loss": 4.4891, - "step": 1493 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023364485981308412, - "loss": 5.1406, - "step": 1494 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023286604361370716, - "loss": 4.7619, - "step": 1495 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023208722741433022, - "loss": 5.6909, - "step": 1496 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023130841121495329, - "loss": 5.0101, - "step": 1497 - }, - { - "epoch": 0.84, - "learning_rate": 0.00023052959501557632, - "loss": 5.1685, - "step": 1498 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022975077881619939, - "loss": 4.605, - "step": 1499 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022897196261682242, - "loss": 5.0912, - "step": 1500 - }, - { - "epoch": 0.84, - "eval_loss": 5.242259502410889, - "eval_runtime": 938.3919, - "eval_samples_per_second": 2.815, - "eval_steps_per_second": 0.353, - "eval_wer": 1.918048393494645, - "step": 1500 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022819314641744548, - "loss": 4.9201, - "step": 1501 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022741433021806855, - "loss": 5.0831, - "step": 1502 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022663551401869158, - "loss": 5.3121, - "step": 1503 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022585669781931465, - "loss": 5.1892, - "step": 1504 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022507788161993768, - "loss": 5.1802, - "step": 1505 - }, - { - "epoch": 0.84, - "learning_rate": 0.00022429906542056075, - "loss": 5.3416, - "step": 1506 - }, - { - "epoch": 0.84, - "learning_rate": 0.0002235202492211838, - "loss": 4.8678, - "step": 1507 - }, - { - "epoch": 0.85, - "learning_rate": 0.00022274143302180685, - "loss": 4.8965, - "step": 1508 - }, - { - "epoch": 0.85, - "learning_rate": 0.0002219626168224299, - "loss": 5.0715, - "step": 1509 - }, - { - "epoch": 0.85, - "learning_rate": 0.00022118380062305295, - "loss": 4.9198, - "step": 1510 - }, - { - "epoch": 0.85, - "learning_rate": 0.000220404984423676, - "loss": 4.7132, - "step": 1511 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021962616822429908, - "loss": 4.9346, - "step": 1512 - }, - { - "epoch": 0.85, - "learning_rate": 0.0002188473520249221, - "loss": 4.6663, - "step": 1513 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021806853582554517, - "loss": 4.8144, - "step": 1514 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021728971962616824, - "loss": 4.7975, - "step": 1515 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021651090342679127, - "loss": 5.3058, - "step": 1516 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021573208722741434, - "loss": 4.7785, - "step": 1517 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021495327102803737, - "loss": 5.3844, - "step": 1518 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021417445482866044, - "loss": 5.2346, - "step": 1519 - }, - { - "epoch": 0.85, - "learning_rate": 0.0002133956386292835, - "loss": 5.2406, - "step": 1520 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021261682242990654, - "loss": 4.8977, - "step": 1521 - }, - { - "epoch": 0.85, - "learning_rate": 0.0002118380062305296, - "loss": 5.1303, - "step": 1522 - }, - { - "epoch": 0.85, - "learning_rate": 0.00021105919003115264, - "loss": 5.6748, - "step": 1523 - }, - { - "epoch": 0.85, - "learning_rate": 0.0002102803738317757, - "loss": 4.7979, - "step": 1524 - }, - { - "epoch": 0.85, - "learning_rate": 0.00020950155763239877, - "loss": 4.804, - "step": 1525 - }, - { - "epoch": 0.86, - "learning_rate": 0.0002087227414330218, - "loss": 4.6933, - "step": 1526 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020794392523364486, - "loss": 5.0428, - "step": 1527 - }, - { - "epoch": 0.86, - "learning_rate": 0.0002071651090342679, - "loss": 4.7932, - "step": 1528 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020638629283489096, - "loss": 4.6617, - "step": 1529 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020560747663551403, - "loss": 4.8229, - "step": 1530 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020482866043613706, - "loss": 4.7727, - "step": 1531 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020404984423676013, - "loss": 4.7603, - "step": 1532 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020327102803738316, - "loss": 5.2585, - "step": 1533 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020249221183800623, - "loss": 4.9258, - "step": 1534 - }, - { - "epoch": 0.86, - "learning_rate": 0.0002017133956386293, - "loss": 5.1086, - "step": 1535 - }, - { - "epoch": 0.86, - "learning_rate": 0.00020093457943925233, - "loss": 4.6404, - "step": 1536 - }, - { - "epoch": 0.86, - "learning_rate": 0.0002001557632398754, - "loss": 5.1445, - "step": 1537 - }, - { - "epoch": 0.86, - "learning_rate": 0.00019937694704049843, - "loss": 5.1859, - "step": 1538 - }, - { - "epoch": 0.86, - "learning_rate": 0.0001985981308411215, - "loss": 4.9457, - "step": 1539 - }, - { - "epoch": 0.86, - "learning_rate": 0.00019781931464174455, - "loss": 5.0712, - "step": 1540 - }, - { - "epoch": 0.86, - "learning_rate": 0.0001970404984423676, - "loss": 5.1834, - "step": 1541 - }, - { - "epoch": 0.86, - "learning_rate": 0.00019626168224299065, - "loss": 4.5998, - "step": 1542 - }, - { - "epoch": 0.86, - "learning_rate": 0.00019548286604361372, - "loss": 5.2259, - "step": 1543 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019470404984423675, - "loss": 4.9743, - "step": 1544 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019392523364485982, - "loss": 5.4056, - "step": 1545 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019314641744548285, - "loss": 4.6837, - "step": 1546 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019236760124610592, - "loss": 5.1801, - "step": 1547 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019158878504672898, - "loss": 4.9865, - "step": 1548 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019080996884735202, - "loss": 5.6618, - "step": 1549 - }, - { - "epoch": 0.87, - "learning_rate": 0.00019003115264797508, - "loss": 4.8826, - "step": 1550 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018925233644859812, - "loss": 5.144, - "step": 1551 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018847352024922118, - "loss": 5.0221, - "step": 1552 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018769470404984424, - "loss": 4.8414, - "step": 1553 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018691588785046728, - "loss": 4.9341, - "step": 1554 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018613707165109034, - "loss": 5.0817, - "step": 1555 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018535825545171338, - "loss": 5.2519, - "step": 1556 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018457943925233644, - "loss": 5.1726, - "step": 1557 - }, - { - "epoch": 0.87, - "learning_rate": 0.0001838006230529595, - "loss": 5.1287, - "step": 1558 - }, - { - "epoch": 0.87, - "learning_rate": 0.00018302180685358254, - "loss": 4.7927, - "step": 1559 - }, - { - "epoch": 0.87, - "learning_rate": 0.0001822429906542056, - "loss": 5.1194, - "step": 1560 - }, - { - "epoch": 0.88, - "learning_rate": 0.00018146417445482864, - "loss": 5.0108, - "step": 1561 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001806853582554517, - "loss": 4.8349, - "step": 1562 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017990654205607477, - "loss": 5.0651, - "step": 1563 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001791277258566978, - "loss": 5.12, - "step": 1564 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017834890965732087, - "loss": 5.0028, - "step": 1565 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001775700934579439, - "loss": 4.8888, - "step": 1566 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017679127725856697, - "loss": 4.6724, - "step": 1567 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017601246105919003, - "loss": 5.0271, - "step": 1568 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017523364485981307, - "loss": 5.1797, - "step": 1569 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017445482866043613, - "loss": 5.0105, - "step": 1570 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001736760124610592, - "loss": 4.8664, - "step": 1571 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017289719626168223, - "loss": 5.1689, - "step": 1572 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001721183800623053, - "loss": 5.0761, - "step": 1573 - }, - { - "epoch": 0.88, - "learning_rate": 0.00017133956386292833, - "loss": 4.7177, - "step": 1574 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001705607476635514, - "loss": 4.7017, - "step": 1575 - }, - { - "epoch": 0.88, - "learning_rate": 0.00016978193146417446, - "loss": 4.9769, - "step": 1576 - }, - { - "epoch": 0.88, - "learning_rate": 0.0001690031152647975, - "loss": 4.8616, - "step": 1577 - }, - { - "epoch": 0.88, - "learning_rate": 0.00016822429906542056, - "loss": 5.0183, - "step": 1578 - }, - { - "epoch": 0.89, - "learning_rate": 0.0001674454828660436, - "loss": 4.9506, - "step": 1579 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016666666666666666, - "loss": 5.6336, - "step": 1580 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016588785046728972, - "loss": 5.1141, - "step": 1581 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016510903426791276, - "loss": 5.066, - "step": 1582 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016433021806853582, - "loss": 4.8829, - "step": 1583 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016355140186915886, - "loss": 4.6577, - "step": 1584 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016277258566978192, - "loss": 4.7851, - "step": 1585 - }, - { - "epoch": 0.89, - "learning_rate": 0.000161993769470405, - "loss": 4.7567, - "step": 1586 - }, - { - "epoch": 0.89, - "learning_rate": 0.00016121495327102802, - "loss": 4.8221, - "step": 1587 - }, - { - "epoch": 0.89, - "learning_rate": 0.0001604361370716511, - "loss": 5.0604, - "step": 1588 - }, - { - "epoch": 0.89, - "learning_rate": 0.00015965732087227412, - "loss": 4.8854, - "step": 1589 - }, - { - "epoch": 0.89, - "learning_rate": 0.0001588785046728972, - "loss": 4.8535, - "step": 1590 - }, - { - "epoch": 0.89, - "learning_rate": 0.00015809968847352025, - "loss": 4.7754, - "step": 1591 - }, - { - "epoch": 0.89, - "learning_rate": 0.0001573208722741433, - "loss": 4.6925, - "step": 1592 - }, - { - "epoch": 0.89, - "learning_rate": 0.00015654205607476635, - "loss": 4.7439, - "step": 1593 - }, - { - "epoch": 0.89, - "learning_rate": 0.0001557632398753894, - "loss": 4.7516, - "step": 1594 - }, - { - "epoch": 0.89, - "learning_rate": 0.00015498442367601245, - "loss": 4.7428, - "step": 1595 - }, - { - "epoch": 0.89, - "learning_rate": 0.00015420560747663551, - "loss": 5.0125, - "step": 1596 - }, - { - "epoch": 0.9, - "learning_rate": 0.00015342679127725855, - "loss": 5.0076, - "step": 1597 - }, - { - "epoch": 0.9, - "learning_rate": 0.00015264797507788161, - "loss": 5.1123, - "step": 1598 - }, - { - "epoch": 0.9, - "learning_rate": 0.00015186915887850468, - "loss": 5.9416, - "step": 1599 - }, - { - "epoch": 0.9, - "learning_rate": 0.00015109034267912771, - "loss": 5.1723, - "step": 1600 - }, - { - "epoch": 0.9, - "learning_rate": 0.00015031152647975078, - "loss": 5.0059, - "step": 1601 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014953271028037381, - "loss": 4.6538, - "step": 1602 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014875389408099688, - "loss": 4.9855, - "step": 1603 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014797507788161994, - "loss": 5.0603, - "step": 1604 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014719626168224298, - "loss": 4.6715, - "step": 1605 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014641744548286604, - "loss": 4.937, - "step": 1606 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014563862928348908, - "loss": 5.0402, - "step": 1607 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014485981308411214, - "loss": 4.8851, - "step": 1608 - }, - { - "epoch": 0.9, - "learning_rate": 0.0001440809968847352, - "loss": 5.0771, - "step": 1609 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014330218068535824, - "loss": 4.7086, - "step": 1610 - }, - { - "epoch": 0.9, - "learning_rate": 0.0001425233644859813, - "loss": 5.0062, - "step": 1611 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014174454828660434, - "loss": 5.1213, - "step": 1612 - }, - { - "epoch": 0.9, - "learning_rate": 0.0001409657320872274, - "loss": 5.0277, - "step": 1613 - }, - { - "epoch": 0.9, - "learning_rate": 0.00014018691588785047, - "loss": 4.7568, - "step": 1614 - }, - { - "epoch": 0.91, - "learning_rate": 0.0001394080996884735, - "loss": 4.8482, - "step": 1615 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013862928348909657, - "loss": 4.7721, - "step": 1616 - }, - { - "epoch": 0.91, - "learning_rate": 0.0001378504672897196, - "loss": 5.1144, - "step": 1617 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013707165109034267, - "loss": 4.792, - "step": 1618 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013629283489096573, - "loss": 4.9042, - "step": 1619 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013551401869158877, - "loss": 4.8169, - "step": 1620 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013473520249221183, - "loss": 5.612, - "step": 1621 - }, - { - "epoch": 0.91, - "learning_rate": 0.0001339563862928349, - "loss": 4.6091, - "step": 1622 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013317757009345793, - "loss": 5.1454, - "step": 1623 - }, - { - "epoch": 0.91, - "learning_rate": 0.000132398753894081, - "loss": 4.9233, - "step": 1624 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013161993769470403, - "loss": 4.9702, - "step": 1625 - }, - { - "epoch": 0.91, - "learning_rate": 0.0001308411214953271, - "loss": 5.0775, - "step": 1626 - }, - { - "epoch": 0.91, - "learning_rate": 0.00013006230529595016, - "loss": 5.0102, - "step": 1627 - }, - { - "epoch": 0.91, - "learning_rate": 0.0001292834890965732, - "loss": 4.7352, - "step": 1628 - }, - { - "epoch": 0.91, - "learning_rate": 0.00012850467289719626, - "loss": 4.9741, - "step": 1629 - }, - { - "epoch": 0.91, - "learning_rate": 0.0001277258566978193, - "loss": 4.7779, - "step": 1630 - }, - { - "epoch": 0.91, - "learning_rate": 0.00012694704049844236, - "loss": 4.7986, - "step": 1631 - }, - { - "epoch": 0.91, - "learning_rate": 0.00012616822429906542, - "loss": 5.1056, - "step": 1632 - }, - { - "epoch": 0.92, - "learning_rate": 0.00012538940809968846, - "loss": 5.3312, - "step": 1633 - }, - { - "epoch": 0.92, - "learning_rate": 0.00012461059190031152, - "loss": 4.7821, - "step": 1634 - }, - { - "epoch": 0.92, - "learning_rate": 0.00012383177570093458, - "loss": 5.0124, - "step": 1635 - }, - { - "epoch": 0.92, - "learning_rate": 0.00012305295950155765, - "loss": 4.8481, - "step": 1636 - }, - { - "epoch": 0.92, - "learning_rate": 0.00012227414330218068, - "loss": 4.8147, - "step": 1637 - }, - { - "epoch": 0.92, - "learning_rate": 0.00012149532710280373, - "loss": 5.3605, - "step": 1638 - }, - { - "epoch": 0.92, - "learning_rate": 0.0001207165109034268, - "loss": 4.6206, - "step": 1639 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011993769470404985, - "loss": 5.3817, - "step": 1640 - }, - { - "epoch": 0.92, - "learning_rate": 0.0001191588785046729, - "loss": 4.8948, - "step": 1641 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011838006230529595, - "loss": 4.824, - "step": 1642 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011760124610591901, - "loss": 4.9077, - "step": 1643 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011682242990654206, - "loss": 4.9438, - "step": 1644 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011604361370716511, - "loss": 5.184, - "step": 1645 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011526479750778816, - "loss": 5.2633, - "step": 1646 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011448598130841121, - "loss": 5.0816, - "step": 1647 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011370716510903427, - "loss": 5.1839, - "step": 1648 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011292834890965732, - "loss": 5.211, - "step": 1649 - }, - { - "epoch": 0.92, - "learning_rate": 0.00011214953271028037, - "loss": 4.9195, - "step": 1650 - }, - { - "epoch": 0.93, - "learning_rate": 0.00011137071651090342, - "loss": 4.9367, - "step": 1651 - }, - { - "epoch": 0.93, - "learning_rate": 0.00011059190031152647, - "loss": 4.9022, - "step": 1652 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010981308411214954, - "loss": 4.9641, - "step": 1653 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010903426791277259, - "loss": 4.807, - "step": 1654 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010825545171339564, - "loss": 4.6811, - "step": 1655 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010747663551401869, - "loss": 4.8929, - "step": 1656 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010669781931464175, - "loss": 5.2187, - "step": 1657 - }, - { - "epoch": 0.93, - "learning_rate": 0.0001059190031152648, - "loss": 4.916, - "step": 1658 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010514018691588785, - "loss": 4.7366, - "step": 1659 - }, - { - "epoch": 0.93, - "learning_rate": 0.0001043613707165109, - "loss": 4.8621, - "step": 1660 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010358255451713395, - "loss": 4.8461, - "step": 1661 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010280373831775701, - "loss": 4.747, - "step": 1662 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010202492211838006, - "loss": 4.6193, - "step": 1663 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010124610591900311, - "loss": 5.0131, - "step": 1664 - }, - { - "epoch": 0.93, - "learning_rate": 0.00010046728971962616, - "loss": 4.665, - "step": 1665 - }, - { - "epoch": 0.93, - "learning_rate": 9.968847352024921e-05, - "loss": 5.038, - "step": 1666 - }, - { - "epoch": 0.93, - "learning_rate": 9.890965732087228e-05, - "loss": 4.8767, - "step": 1667 - }, - { - "epoch": 0.93, - "learning_rate": 9.813084112149533e-05, - "loss": 4.7492, - "step": 1668 - }, - { - "epoch": 0.94, - "learning_rate": 9.735202492211838e-05, - "loss": 4.6852, - "step": 1669 - }, - { - "epoch": 0.94, - "learning_rate": 9.657320872274143e-05, - "loss": 5.0729, - "step": 1670 - }, - { - "epoch": 0.94, - "learning_rate": 9.579439252336449e-05, - "loss": 4.8921, - "step": 1671 - }, - { - "epoch": 0.94, - "learning_rate": 9.501557632398754e-05, - "loss": 5.5359, - "step": 1672 - }, - { - "epoch": 0.94, - "learning_rate": 9.423676012461059e-05, - "loss": 4.8785, - "step": 1673 - }, - { - "epoch": 0.94, - "learning_rate": 9.345794392523364e-05, - "loss": 4.8677, - "step": 1674 - }, - { - "epoch": 0.94, - "learning_rate": 9.267912772585669e-05, - "loss": 5.2157, - "step": 1675 - }, - { - "epoch": 0.94, - "learning_rate": 9.190031152647975e-05, - "loss": 4.6123, - "step": 1676 - }, - { - "epoch": 0.94, - "learning_rate": 9.11214953271028e-05, - "loss": 4.5767, - "step": 1677 - }, - { - "epoch": 0.94, - "learning_rate": 9.034267912772585e-05, - "loss": 4.7704, - "step": 1678 - }, - { - "epoch": 0.94, - "learning_rate": 8.95638629283489e-05, - "loss": 5.0619, - "step": 1679 - }, - { - "epoch": 0.94, - "learning_rate": 8.878504672897195e-05, - "loss": 5.2323, - "step": 1680 - }, - { - "epoch": 0.94, - "learning_rate": 8.800623052959502e-05, - "loss": 4.5179, - "step": 1681 - }, - { - "epoch": 0.94, - "learning_rate": 8.722741433021807e-05, - "loss": 4.5293, - "step": 1682 - }, - { - "epoch": 0.94, - "learning_rate": 8.644859813084112e-05, - "loss": 4.9469, - "step": 1683 - }, - { - "epoch": 0.94, - "learning_rate": 8.566978193146417e-05, - "loss": 4.6941, - "step": 1684 - }, - { - "epoch": 0.94, - "learning_rate": 8.489096573208723e-05, - "loss": 4.8172, - "step": 1685 - }, - { - "epoch": 0.95, - "learning_rate": 8.411214953271028e-05, - "loss": 4.793, - "step": 1686 - }, - { - "epoch": 0.95, - "learning_rate": 8.333333333333333e-05, - "loss": 4.8156, - "step": 1687 - }, - { - "epoch": 0.95, - "learning_rate": 8.255451713395638e-05, - "loss": 5.0305, - "step": 1688 - }, - { - "epoch": 0.95, - "learning_rate": 8.177570093457943e-05, - "loss": 4.8577, - "step": 1689 - }, - { - "epoch": 0.95, - "learning_rate": 8.09968847352025e-05, - "loss": 4.589, - "step": 1690 - }, - { - "epoch": 0.95, - "learning_rate": 8.021806853582554e-05, - "loss": 5.0832, - "step": 1691 - }, - { - "epoch": 0.95, - "learning_rate": 7.94392523364486e-05, - "loss": 4.8546, - "step": 1692 - }, - { - "epoch": 0.95, - "learning_rate": 7.866043613707164e-05, - "loss": 5.1167, - "step": 1693 - }, - { - "epoch": 0.95, - "learning_rate": 7.78816199376947e-05, - "loss": 5.1777, - "step": 1694 - }, - { - "epoch": 0.95, - "learning_rate": 7.710280373831776e-05, - "loss": 5.1985, - "step": 1695 - }, - { - "epoch": 0.95, - "learning_rate": 7.632398753894081e-05, - "loss": 7.0248, - "step": 1696 - }, - { - "epoch": 0.95, - "learning_rate": 7.554517133956386e-05, - "loss": 4.7882, - "step": 1697 - }, - { - "epoch": 0.95, - "learning_rate": 7.476635514018691e-05, - "loss": 5.2036, - "step": 1698 - }, - { - "epoch": 0.95, - "learning_rate": 7.398753894080997e-05, - "loss": 5.277, - "step": 1699 - }, - { - "epoch": 0.95, - "learning_rate": 7.320872274143302e-05, - "loss": 5.1742, - "step": 1700 - }, - { - "epoch": 0.95, - "learning_rate": 7.242990654205607e-05, - "loss": 5.5518, - "step": 1701 - }, - { - "epoch": 0.95, - "learning_rate": 7.165109034267912e-05, - "loss": 4.7879, - "step": 1702 - }, - { - "epoch": 0.95, - "learning_rate": 7.087227414330217e-05, - "loss": 4.7595, - "step": 1703 - }, - { - "epoch": 0.96, - "learning_rate": 7.009345794392523e-05, - "loss": 4.8525, - "step": 1704 - }, - { - "epoch": 0.96, - "learning_rate": 6.931464174454828e-05, - "loss": 4.8597, - "step": 1705 - }, - { - "epoch": 0.96, - "learning_rate": 6.853582554517133e-05, - "loss": 4.5263, - "step": 1706 - }, - { - "epoch": 0.96, - "learning_rate": 6.775700934579438e-05, - "loss": 4.6897, - "step": 1707 - }, - { - "epoch": 0.96, - "learning_rate": 6.697819314641745e-05, - "loss": 5.0124, - "step": 1708 - }, - { - "epoch": 0.96, - "learning_rate": 6.61993769470405e-05, - "loss": 5.2334, - "step": 1709 - }, - { - "epoch": 0.96, - "learning_rate": 6.542056074766355e-05, - "loss": 5.0503, - "step": 1710 - }, - { - "epoch": 0.96, - "learning_rate": 6.46417445482866e-05, - "loss": 4.591, - "step": 1711 - }, - { - "epoch": 0.96, - "learning_rate": 6.386292834890965e-05, - "loss": 4.9236, - "step": 1712 - }, - { - "epoch": 0.96, - "learning_rate": 6.308411214953271e-05, - "loss": 5.2821, - "step": 1713 - }, - { - "epoch": 0.96, - "learning_rate": 6.230529595015576e-05, - "loss": 4.876, - "step": 1714 - }, - { - "epoch": 0.96, - "learning_rate": 6.152647975077882e-05, - "loss": 4.7723, - "step": 1715 - }, { "epoch": 0.96, - "learning_rate": 6.074766355140187e-05, - "loss": 5.0203, - "step": 1716 - }, - { - "epoch": 0.96, - "learning_rate": 5.9968847352024924e-05, - "loss": 5.2117, - "step": 1717 - }, - { - "epoch": 0.96, - "learning_rate": 5.9190031152647974e-05, - "loss": 5.355, - "step": 1718 - }, - { - "epoch": 0.96, - "learning_rate": 5.841121495327103e-05, - "loss": 4.9818, - "step": 1719 + "learning_rate": 9.183673469387756e-05, + "loss": 4.6767, + "step": 858 }, { "epoch": 0.96, - "learning_rate": 5.763239875389408e-05, - "loss": 4.7752, - "step": 1720 + "learning_rate": 8.928571428571429e-05, + "loss": 4.4785, + "step": 859 }, { "epoch": 0.96, - "learning_rate": 5.685358255451714e-05, - "loss": 4.8968, - "step": 1721 - }, - { - "epoch": 0.97, - "learning_rate": 5.607476635514019e-05, - "loss": 5.0031, - "step": 1722 - }, - { - "epoch": 0.97, - "learning_rate": 5.529595015576324e-05, - "loss": 5.0141, - "step": 1723 - }, - { - "epoch": 0.97, - "learning_rate": 5.4517133956386294e-05, - "loss": 4.8312, - "step": 1724 - }, - { - "epoch": 0.97, - "learning_rate": 5.3738317757009344e-05, - "loss": 4.842, - "step": 1725 - }, - { - "epoch": 0.97, - "learning_rate": 5.29595015576324e-05, - "loss": 4.7347, - "step": 1726 - }, - { - "epoch": 0.97, - "learning_rate": 5.218068535825545e-05, - "loss": 5.0622, - "step": 1727 - }, - { - "epoch": 0.97, - "learning_rate": 5.140186915887851e-05, - "loss": 4.9378, - "step": 1728 - }, - { - "epoch": 0.97, - "learning_rate": 5.062305295950156e-05, - "loss": 5.2907, - "step": 1729 - }, - { - "epoch": 0.97, - "learning_rate": 4.984423676012461e-05, - "loss": 4.9128, - "step": 1730 + "learning_rate": 8.673469387755102e-05, + "loss": 4.6034, + "step": 860 }, { "epoch": 0.97, - "learning_rate": 4.9065420560747664e-05, - "loss": 4.4455, - "step": 1731 + "learning_rate": 8.418367346938775e-05, + "loss": 4.926, + "step": 861 }, { "epoch": 0.97, - "learning_rate": 4.8286604361370714e-05, - "loss": 4.62, - "step": 1732 + "learning_rate": 8.163265306122449e-05, + "loss": 4.6059, + "step": 862 }, { "epoch": 0.97, - "learning_rate": 4.750778816199377e-05, - "loss": 4.7372, - "step": 1733 + "learning_rate": 7.908163265306123e-05, + "loss": 4.6713, + "step": 863 }, { "epoch": 0.97, - "learning_rate": 4.672897196261682e-05, - "loss": 4.9109, - "step": 1734 + "learning_rate": 7.653061224489797e-05, + "loss": 4.9771, + "step": 864 }, { "epoch": 0.97, - "learning_rate": 4.595015576323988e-05, - "loss": 5.2291, - "step": 1735 + "learning_rate": 7.39795918367347e-05, + "loss": 4.7271, + "step": 865 }, { "epoch": 0.97, - "learning_rate": 4.517133956386293e-05, - "loss": 5.5436, - "step": 1736 + "learning_rate": 7.142857142857142e-05, + "loss": 4.7206, + "step": 866 }, { "epoch": 0.97, - "learning_rate": 4.439252336448598e-05, - "loss": 4.4576, - "step": 1737 + "learning_rate": 6.887755102040816e-05, + "loss": 4.7444, + "step": 867 }, { "epoch": 0.97, - "learning_rate": 4.3613707165109034e-05, - "loss": 4.9642, - "step": 1738 + "learning_rate": 6.63265306122449e-05, + "loss": 4.6091, + "step": 868 }, { "epoch": 0.97, - "learning_rate": 4.2834890965732084e-05, - "loss": 4.8552, - "step": 1739 - }, - { - "epoch": 0.98, - "learning_rate": 4.205607476635514e-05, - "loss": 4.7389, - "step": 1740 - }, - { - "epoch": 0.98, - "learning_rate": 4.127725856697819e-05, - "loss": 4.8911, - "step": 1741 - }, - { - "epoch": 0.98, - "learning_rate": 4.049844236760125e-05, - "loss": 4.8404, - "step": 1742 - }, - { - "epoch": 0.98, - "learning_rate": 3.97196261682243e-05, - "loss": 4.5837, - "step": 1743 - }, - { - "epoch": 0.98, - "learning_rate": 3.894080996884735e-05, - "loss": 4.7072, - "step": 1744 - }, - { - "epoch": 0.98, - "learning_rate": 3.8161993769470404e-05, - "loss": 4.9044, - "step": 1745 - }, - { - "epoch": 0.98, - "learning_rate": 3.7383177570093454e-05, - "loss": 4.9988, - "step": 1746 - }, - { - "epoch": 0.98, - "learning_rate": 3.660436137071651e-05, - "loss": 4.905, - "step": 1747 - }, - { - "epoch": 0.98, - "learning_rate": 3.582554517133956e-05, - "loss": 4.6587, - "step": 1748 + "learning_rate": 6.377551020408164e-05, + "loss": 4.5961, + "step": 869 }, { "epoch": 0.98, - "learning_rate": 3.504672897196262e-05, - "loss": 4.8372, - "step": 1749 + "learning_rate": 6.122448979591836e-05, + "loss": 4.6923, + "step": 870 }, { "epoch": 0.98, - "learning_rate": 3.426791277258567e-05, - "loss": 4.8845, - "step": 1750 + "learning_rate": 5.8673469387755104e-05, + "loss": 4.5866, + "step": 871 }, { "epoch": 0.98, - "learning_rate": 3.3489096573208724e-05, - "loss": 4.6127, - "step": 1751 + "learning_rate": 5.6122448979591836e-05, + "loss": 4.6059, + "step": 872 }, { "epoch": 0.98, - "learning_rate": 3.2710280373831774e-05, - "loss": 4.7692, - "step": 1752 + "learning_rate": 5.357142857142857e-05, + "loss": 4.6245, + "step": 873 }, { "epoch": 0.98, - "learning_rate": 3.1931464174454823e-05, - "loss": 4.9454, - "step": 1753 + "learning_rate": 5.102040816326531e-05, + "loss": 4.592, + "step": 874 }, { "epoch": 0.98, - "learning_rate": 3.115264797507788e-05, - "loss": 4.9908, - "step": 1754 + "learning_rate": 4.846938775510204e-05, + "loss": 4.7475, + "step": 875 }, { "epoch": 0.98, - "learning_rate": 3.0373831775700934e-05, - "loss": 4.9819, - "step": 1755 + "learning_rate": 4.591836734693878e-05, + "loss": 4.4702, + "step": 876 }, { "epoch": 0.98, - "learning_rate": 2.9595015576323987e-05, - "loss": 4.6379, - "step": 1756 + "learning_rate": 4.336734693877551e-05, + "loss": 4.4525, + "step": 877 }, { "epoch": 0.98, - "learning_rate": 2.881619937694704e-05, - "loss": 4.7726, - "step": 1757 - }, - { - "epoch": 0.99, - "learning_rate": 2.8037383177570094e-05, - "loss": 4.5652, - "step": 1758 - }, - { - "epoch": 0.99, - "learning_rate": 2.7258566978193147e-05, - "loss": 5.02, - "step": 1759 - }, - { - "epoch": 0.99, - "learning_rate": 2.64797507788162e-05, - "loss": 4.8819, - "step": 1760 - }, - { - "epoch": 0.99, - "learning_rate": 2.5700934579439254e-05, - "loss": 4.9836, - "step": 1761 - }, - { - "epoch": 0.99, - "learning_rate": 2.4922118380062303e-05, - "loss": 4.6194, - "step": 1762 - }, - { - "epoch": 0.99, - "learning_rate": 2.4143302180685357e-05, - "loss": 4.8143, - "step": 1763 - }, - { - "epoch": 0.99, - "learning_rate": 2.336448598130841e-05, - "loss": 5.055, - "step": 1764 - }, - { - "epoch": 0.99, - "learning_rate": 2.2585669781931463e-05, - "loss": 4.6614, - "step": 1765 - }, - { - "epoch": 0.99, - "learning_rate": 2.1806853582554517e-05, - "loss": 4.7388, - "step": 1766 + "learning_rate": 4.0816326530612245e-05, + "loss": 4.6854, + "step": 878 }, { "epoch": 0.99, - "learning_rate": 2.102803738317757e-05, - "loss": 4.8337, - "step": 1767 + "learning_rate": 3.8265306122448984e-05, + "loss": 4.6533, + "step": 879 }, { "epoch": 0.99, - "learning_rate": 2.0249221183800623e-05, - "loss": 4.6581, - "step": 1768 + "learning_rate": 3.571428571428571e-05, + "loss": 4.9238, + "step": 880 }, { "epoch": 0.99, - "learning_rate": 1.9470404984423673e-05, - "loss": 4.7557, - "step": 1769 + "learning_rate": 3.316326530612245e-05, + "loss": 4.4336, + "step": 881 }, { "epoch": 0.99, - "learning_rate": 1.8691588785046727e-05, - "loss": 4.6828, - "step": 1770 + "learning_rate": 3.061224489795918e-05, + "loss": 4.6463, + "step": 882 }, { "epoch": 0.99, - "learning_rate": 1.791277258566978e-05, - "loss": 4.6802, - "step": 1771 + "learning_rate": 2.8061224489795918e-05, + "loss": 4.5835, + "step": 883 }, { "epoch": 0.99, - "learning_rate": 1.7133956386292833e-05, - "loss": 4.6912, - "step": 1772 + "learning_rate": 2.5510204081632654e-05, + "loss": 4.5467, + "step": 884 }, { "epoch": 0.99, - "learning_rate": 1.6355140186915887e-05, - "loss": 4.7784, - "step": 1773 + "learning_rate": 2.295918367346939e-05, + "loss": 4.5758, + "step": 885 }, { "epoch": 0.99, - "learning_rate": 1.557632398753894e-05, - "loss": 4.8006, - "step": 1774 + "learning_rate": 2.0408163265306123e-05, + "loss": 4.664, + "step": 886 }, { "epoch": 0.99, - "learning_rate": 1.4797507788161993e-05, - "loss": 4.6394, - "step": 1775 - }, - { - "epoch": 1.0, - "learning_rate": 1.4018691588785047e-05, - "loss": 4.793, - "step": 1776 - }, - { - "epoch": 1.0, - "learning_rate": 1.32398753894081e-05, - "loss": 5.185, - "step": 1777 - }, - { - "epoch": 1.0, - "learning_rate": 1.2461059190031152e-05, - "loss": 4.8303, - "step": 1778 - }, - { - "epoch": 1.0, - "learning_rate": 1.1682242990654205e-05, - "loss": 5.2742, - "step": 1779 + "learning_rate": 1.7857142857142855e-05, + "loss": 4.5767, + "step": 887 }, { "epoch": 1.0, - "learning_rate": 1.0903426791277258e-05, - "loss": 4.9136, - "step": 1780 + "learning_rate": 1.530612244897959e-05, + "loss": 4.7443, + "step": 888 }, { "epoch": 1.0, - "learning_rate": 1.0124610591900312e-05, - "loss": 5.0697, - "step": 1781 + "learning_rate": 1.2755102040816327e-05, + "loss": 4.7622, + "step": 889 }, { "epoch": 1.0, - "learning_rate": 9.345794392523363e-06, - "loss": 4.8058, - "step": 1782 + "learning_rate": 1.0204081632653061e-05, + "loss": 4.4401, + "step": 890 }, { "epoch": 1.0, - "learning_rate": 8.566978193146417e-06, - "loss": 4.9048, - "step": 1783 + "learning_rate": 7.653061224489796e-06, + "loss": 4.8296, + "step": 891 }, { "epoch": 1.0, - "learning_rate": 7.78816199376947e-06, - "loss": 4.0566, - "step": 1784 + "learning_rate": 5.102040816326531e-06, + "loss": 4.2487, + "step": 892 }, { "epoch": 1.0, - "step": 1784, + "step": 892, "total_flos": 0.0, - "train_loss": 7.005254806691756, - "train_runtime": 8711.5909, - "train_samples_per_second": 3.276, - "train_steps_per_second": 0.205 + "train_loss": 4.944881099221952, + "train_runtime": 6324.9374, + "train_samples_per_second": 4.512, + "train_steps_per_second": 0.141 } ], - "max_steps": 1784, + "max_steps": 892, "num_train_epochs": 1, "total_flos": 0.0, "trial_name": null,